PersonaBias/persona-bias-outputs
Updated • 2.16k
Persona Bias MI
community
AI & ML interests
Mechanistic Interpretability
Recent Activity
PersonaBias/Original-no-persona-replacement-remainder
Viewer • Updated • 234k • 180
PersonaBias/Original-hybrid-train-no-persona-mean
Viewer • Updated • 250k • 129
PersonaBias/Original-hybrid-shared-no-persona-remainder
Viewer • Updated • 250k • 54
PersonaBias/Original-hybrid-correct-train-no-persona-mean
Viewer • Updated • 231k • 94
PersonaBias/Original-circuit-discovery
Viewer • Updated • 74.7k • 38
PersonaBias/Original-baseline-bias-unbias
Viewer • Updated • 428k • 30
PersonaBias/Original-alpha-suppression-task-boost
Viewer • Updated • 755k • 147
PersonaBias/Original-alpha-beta-no-outside
Updated • 320
PersonaBias/Reverse-no-persona-replacement-remainder
Viewer • Updated • 555k • 112
PersonaBias/Reverse-hybrid-train-no-persona-mean
Viewer • Updated • 379k • 94
PersonaBias/Reverse-hybrid-shared-no-persona-remainder
Viewer • Updated • 589k • 203
PersonaBias/Reverse-hybrid-correct-train-no-persona-mean
Viewer • Updated • 568k • 106
PersonaBias/Reverse-circuit-discovery
Viewer • Updated • 69.8k • 101
PersonaBias/Reverse-baseline-bias-unbias
Viewer • Updated • 5.95M • 189
PersonaBias/Reverse-alpha-suppression-task-boost
Viewer • Updated • 6.49M • 138
PersonaBias/Reverse-alpha-beta-no-outside
Viewer • Updated • 75.2k • 202
PersonaBias/counterfactuals
Viewer • Updated • 505k • 197
PersonaBias/bias_evaluation_sets
Viewer • Updated • 281k • 45
PersonaBias/output
Viewer • Updated • 592k • 12