Pinned Loading

1. othello_world othello_world Public

   Emergent world representations: Exploring a sequence model trained on a synthetic task

   Jupyter Notebook 172 40

2. honest_llama honest_llama Public

   Inference-Time Intervention: Eliciting Truthful Answers from a Language Model

   Python 488 38

3. persona_drift persona_drift Public

   Measuring and Controlling Persona Drift in Language Model Dialogs

   Python 14 3

4. q_probe q_probe Public

   Q-Probe: A Lightweight Approach to Reward Maximization for Language Models

   Jupyter Notebook 40 1

5. dialogue_action_token dialogue_action_token Public

   Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner

   Python 20 1