Sync with data tooling repo, using edugp/kenlm models, updating viz to use quantiles for coloring and ad-hoc viz for the registry dataset

Run tokenizer before computing perplexity and format

Add CLI and refactor

Use latest embedding-lenses

Upgrade dependencies to match embedding-lenses

Upgrade streamlit

Install embedding-lenses from wheel

Do not lock the version of embedding-lenses

Update requirements.txt to install kenlm

Inital commit for perplexity lenses