LLM explorables

Small sketches that show how a language model works, one part at a time. Each lets you change something and watch what happens.

1. Text Completions Animation

   Next-token prediction. The prompt goes to a completion model, the twenty likeliest next tokens come back with their probabilities, and you pick one — or let the timer pick the top one every second. Presentation mode

2. Temperature and Sampling

   The same twenty candidates rescaled across temperatures from 0 to 2, and a token sampled from them.

3. Token + TokenID Pairs

   The vocabulary: every cl100k_base token as a coloured box; hover one for its id.

4. Tokenizer Map

   A reference rather than a demonstration: a network of every model on OpenRouter and the tokenizer vocabulary it actually uses, click any node for its evidence and source.

5. Semantic Embeddings Comparison

   Two texts as vectors of 1,536 numbers, drawn as coloured lines, with their per-dimension difference and their cosine similarity.