Pinned Loading

1. Gaslight_EVAL Gaslight_EVAL Public

   AI safety evaluation framework testing LLM epistemic robustness under adversarial self-history manipulation

   Python 1

2. Secret_H_Evals Secret_H_Evals Public

   Multi-agent strategic deception evaluation framework for LLMs using Secret Hitler as a testbed. Analyzes AI reasoning, trust dynamics, and deceptive behavior patterns.

   Python 1

3. Pinocchio-Vector-Test Pinocchio-Vector-Test Public

   Investigating whether language models encode anticipated social consequences in their activations. Uses a 2x2 factorial design crossing truth × social valence to show that models are more sensitive…

   Python 1

4. NeuroMap NeuroMap Public

   Mechanistic interpretability framework for recovering algorithmic structure in neural networks. Includes causal verification, Fourier analysis, and circuit discovery for understanding how transform…

   Python 1

5. Mamba_KAN Mamba_KAN Public

   A rigorous 2x3 factorial comparison of neural network architectures: KAN vs MLP feedforward layers combined with Transformer vs Mamba sequence models. Investigates whether KAN advantages stem from …

   Python 1

6. model_convergence model_convergence Public

   HTML 1