Runs in your browser. Nothing you enter is uploaded or logged.
Next-token sampling simulator
Temperature, top-k and top-p, visualised.
One useful email every Monday
New free tools, AI and network threats that matter, and one quick challenge. No spam, unsubscribe in one click.
Questions people ask
What does temperature do in an LLM?
It flattens or sharpens the probability of the next token. Low temperature gives predictable text, high temperature gives varied text.
Related tools
- How an LLM writes a sentenceTokens, embeddings, attention and sampling, one animated step at a time.
- How prompt injection worksFollow a hidden instruction into an AI agent, and see where each defense stops it.
- Neural network playgroundTrain a network live and watch it learn.
- Gradient descent visualizerSee learning rate and momentum in action.
- Tokenizer explorerReal GPT tokenizers, in many languages.
Link to this tool
Found it useful? Paste this into your blog, wiki or runbook.
<a href="https://toolbini.com/learn/sampling-simulator/">Next-token sampling simulator</a>Reviewed by the editorial team · Last reviewed 2026-11 · Report an error