Safety icons

The 8 safety icons in AI & LLM, described

Biasbias

Bias — the scales are not even, a skew in data or outcomes that fairness work corrects.

Bias checkbias-check

A bias check — does the model treat like cases alike, a fairness audit.

Content filtercontent-filter

A content filter — the moderation screen that decides what is not allowed through.

Guardrailguardrail

A guardrail — a safety limit the model's output is not allowed to cross.

Hallucinationhallucination

A hallucination — an answer said with confidence that is true of nothing, invented.

Refusalrefusal

A refusal — the model declined the request, it will not do that.

Safety checksafety-check

A safety check — output looked at and screened before it goes out.

Toxicitytoxicity

Toxicity — harmful or abusive content that should not have been said, flagged.

In code, each is one import — import { Bias } from "@iconmind/react/icons/bias" — and the same name in Vue, Svelte, Solid, Preact, React Native, Astro, Blade and Flutter.

Narrow it by tag