Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Extracting spatial and temporal world models from LLMs
| Date | Stars |
|---|---|
| 2026-07-31 | 262 |
| 2026-08-06 | 262 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# World Models in LLMs
Official code repository for the paper "Language Models Represent Space and Time" by Wes Gurnee and Max Tegmark.
This repository contains all experimental infrastructure for the paper. We expect most users to just be interested in the cleaned data CSVs containing entity names and relevant metadata. These can be found in `data/entity_datasets/` (with the tokenized versions for Llama and Pythia models available in the `data/prompt_datasets/` folder for each prompt type).
In the coming weeks we will release a minimal version of the code to run basic probing experiments on our datasets.
## Cite
If you found our code our datasets helpful in your research, please cite our paper
```
@article{gurnee2023language,
title={Language Models Represent Space and Time},
author={Gurnee, Wes and Tegmark, Max},
journal={arXiv preprint arXiv:2310.02207},
year={2023}
}
```
Excerpt of 900 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:b6272cf9a15238ec, llm:description: 'Extracting spatial and temporal world models from LLMs' (repository description)
matched fp:b6272cf9a15238ec, llm:description: 'Extracting spatial and temporal world models from LLMs' (repository description)
matched fp:b6272cf9a15238ec, llm:description: 'Extracting spatial and temporal world models from LLMs' (repository description)