PersonaBias/persona-bias-outputs-20260914
Preview • Updated • 41
Persona Bias MI
community
AI & ML interests
Mechanistic Interpretability
Recent Activity
View all activity
PersonaBias/alpha_beta_intervention
Viewer • Updated • 17.2k • 52
PersonaBias/persona-bias-outputs
Updated • 465
PersonaBias/Original-no-persona-replacement-remainder
Viewer • Updated • 234k • 181
PersonaBias/Original-hybrid-train-no-persona-mean
Viewer • Updated • 250k • 135
PersonaBias/Original-hybrid-shared-no-persona-remainder
Viewer • Updated • 250k • 171
PersonaBias/Original-hybrid-correct-train-no-persona-mean
Viewer • Updated • 231k • 139
PersonaBias/Original-circuit-discovery
Viewer • Updated • 74.7k • 81
PersonaBias/Original-baseline-bias-unbias
Viewer • Updated • 428k • 53
PersonaBias/Original-alpha-suppression-task-boost
Viewer • Updated • 755k • 185
PersonaBias/Original-alpha-beta-no-outside
Updated • 378
PersonaBias/Reverse-no-persona-replacement-remainder
Viewer • Updated • 555k • 125
PersonaBias/Reverse-hybrid-train-no-persona-mean
Viewer • Updated • 379k • 135
PersonaBias/Reverse-hybrid-shared-no-persona-remainder
Viewer • Updated • 589k • 264
PersonaBias/Reverse-hybrid-correct-train-no-persona-mean
Viewer • Updated • 568k • 116
PersonaBias/Reverse-circuit-discovery
Viewer • Updated • 69.8k • 138
PersonaBias/Reverse-baseline-bias-unbias
Viewer • Updated • 5.95M • 165
PersonaBias/Reverse-alpha-suppression-task-boost
Viewer • Updated • 6.49M • 168
PersonaBias/Reverse-alpha-beta-no-outside
Viewer • Updated • 75.2k • 262
PersonaBias/counterfactuals
Viewer • Updated • 505k • 198
PersonaBias/bias_evaluation_sets
Viewer • Updated • 281k • 44
PersonaBias/output
Viewer • Updated • 592k • 8