PPL
Mor Geva
Papers (4)
Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground TruthMechanistically Interpretable Neural Encoding Reveals Fine-Grained Functional Selectivity in Human Visual CortexRouters Learn the Geometry of Their Experts: Geometric Coupling in Sparse Mixture-of-ExpertsData-driven Circuit Discovery for Interpretability of Language Models