Nerdy Stuff

Under the hood explorations. See how AI actually works with interactive visualizations.

Visualize how words and sentences cluster in vector space. See semantic similarity in action.

My Turkish-optimized tokenizer. Compare with GPT-4 and see ~45% token savings on Turkish text.

Compare tokenization across GPT, Llama, Claude, and more. See why token counts differ.

Visualize where transformer models look when processing text. See attention patterns.

See the top candidate tokens at each generation step. Understand how LLMs make choices.

Same prompt, different temperatures. See how randomness affects model output.

My personal N-Gram model. Old school meets new school language modeling.