Glossary

AI Detection Glossary

Plain-English definitions of the terms behind AI detectors and AI humanizers, from perplexity and burstiness to false positives and watermarking. Each one links to a deeper guide or a free tool.

Try the free AI detector

A

Academic integrity policy

A school's rules on what counts as your own work, including whether and how AI tools may be used. Policies differ between institutions and even between courses, so the policy for your class is the one that applies.

AI humanizers and academic policies

AI detector

A tool that estimates whether text was written by an AI model. Detectors such as GPTZero, Turnitin and ZeroGPT score statistical patterns like word predictability and sentence variation. They give a probability, not proof of who wrote the text.

How AI detectors workFree AI detector

AI humanizer

A tool that rewrites AI-generated text so it reads like natural human writing. Unlike a paraphraser, a humanizer changes the sentence rhythm, structure and word choice that AI detectors measure, while keeping the original meaning.

The HumanizerHumanizer vs paraphraser

AI paraphrasing detection

A detector feature that looks for text that was generated by AI and then reworded by a paraphrasing tool. Turnitin reports this kind of text separately in its AI writing report.

Can Turnitin detect QuillBot?

AI score

The number an AI detector reports for a piece of text, usually the share of the text it believes is AI-generated or the probability that it is. Scores from different detectors aren't comparable, and none of them prove authorship.

Turnitin AI score explained

AI tells

Patterns that make text read as machine-written: stock phrases like 'plays a crucial role', words like 'delve' and 'tapestry', formulaic transitions, rule-of-three lists and heavy em dash use. Readers notice them, and detectors pick up the predictability behind them.

AI word checkerWhy ChatGPT uses em dashes

B

Burstiness

How much sentence length and structure vary through a piece of writing. Human writing tends to mix long and short sentences, while AI output is often even. GPTZero popularized it as an AI signal, and modern detectors still respond to it.

Sentence length checkerPerplexity and burstiness explained

C

Classifier

A machine learning model trained to sort inputs into categories. Most AI detectors are classifiers trained on examples of human and AI writing, which learn to label new text as one or the other.

How AI detectors work

E

Em dash

The long dash (—) used to set off a phrase. Human writers use it too, but heavy em dash use has become a well-known sign of unedited ChatGPT output. Removing em dashes alone doesn't change an AI detector score.

ChatGPT text cleanerWhy ChatGPT uses em dashes

F

False negative

When an AI detector labels AI-generated text as human-written. Edited, mixed or humanized text is the most common cause.

Which detector is strictest?

G

Generative AI

AI systems that create new content such as text, images or code from a prompt. ChatGPT, Claude, Gemini, Copilot and Grok are generative AI tools for text.

Humanize ChatGPT text

GPT

Short for generative pre-trained transformer, the family of large language models from OpenAI that powers ChatGPT. People often use 'GPT' loosely to mean any AI text generator.

ChatGPT humanizer

H

Hallucination

When an AI model states something false or invents details, such as fake citations, with confidence. Humanizing doesn't fix hallucinations, so always check facts, figures and sources in AI-assisted work.

Humanize a research paper

Hidden characters

Invisible or look-alike Unicode characters, such as zero-width spaces and narrow no-break spaces, that can appear in copied text. They aren't a reliable AI watermark, but they can cause odd spacing and are easy to remove.

Remove hidden characters

Humanize

To rewrite AI-generated text so it sounds like a person wrote it: varied sentence rhythm, natural word choice and fewer stock phrases, with the meaning unchanged. You can humanize by hand or with an AI humanizer.

Humanize AI text manuallyFree AI humanizer

L

Large language model (LLM)

An AI model trained on large amounts of text to predict the next word, or token, in a sequence. LLMs power chatbots like ChatGPT, Claude and Gemini, and their tendency to choose likely words is what detectors look for.

How detectors spot LLM text

Know the terms? Fix the text.

The Humanizer rewrites the perplexity and burstiness patterns detectors measure, while keeping your meaning. 350 free words every month.

See plans & pricing
  • 350 free words every month
  • No credit card required
  • Sign in with Google in one click

P

Paraphraser

A tool, such as QuillBot, that rewords text by swapping words and rearranging phrases. Paraphrasing usually keeps the underlying sentence structure, so paraphrased AI text can still be flagged by detectors.

Humanizer vs paraphraserThe Humanizer vs QuillBot

Perplexity

A measure of how predictable a text is to a language model. Low perplexity means each word is the one a model would expect, which is typical of AI output. It was an early core signal for detectors, and today's trained models still pick up the predictability it measures.

Perplexity and burstiness explained

Prompt

The instruction or question you give an AI model. Better prompts can make AI drafts sound more natural, but prompting alone rarely removes the patterns detectors measure.

ChatGPT prompts to sound human

R

Readability score

A number estimating how easy text is to read. The Flesch reading ease score runs from 0 to 100, where higher is easier, and grade-level formulas estimate the years of schooling needed. Readable text is not automatically human-sounding.

Readability checker

S

Sentence length variation

How much the number of words per sentence changes from one sentence to the next. It's the easiest part of burstiness to see and fix: a run of similar-length sentences is a common AI tell.

Sentence length checker

Similarity score

Turnitin's plagiarism measure: the share of a submission that matches existing sources. It's separate from the AI writing score, so original AI-generated text can have a low similarity score and a high AI score.

Turnitin AI score explained

Supercharged mode

The Humanizer's setting for long texts. Free and Basic plans humanize up to 400 words per run; with Supercharged mode, Pro and Ultimate users can humanize longer texts in one pass with a consistent voice.

Plans and pricing

T

Temperature

A setting that controls how random an AI model's word choices are. Low temperature produces safer, more predictable text, which detectors find easier to flag. Higher temperature adds variety but can reduce accuracy.

How AI detectors work

Token

The unit of text a language model reads and writes, often a word or part of a word. Models generate text one token at a time by picking from likely options, which is the source of the predictability detectors measure.

Perplexity explained

U

V

W

Watermarking

Embedding a hidden statistical signal in AI-generated text, usually by nudging word choices, so the text can later be identified as AI-written. It's an active research area, and a watermark only helps if the checker has access to the provider's method.

The AI detection arms race

Keep learning

Guides that go deeper

Make your AI text sound human for free

Paste text from ChatGPT, Claude or Gemini and get natural writing designed to pass GPTZero, Turnitin and other AI detectors.

See plans & pricing
  • 350 free words every month
  • No credit card required
  • Sign in with Google in one click