Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to gender bias in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tabor
    -0.79
     Hawley
    -0.74
     Elis
    -0.73
    Griffin
    -0.73
     Terra
    -0.68
     Charlton
    -0.68
     Griffin
    -0.67
     Zee
    -0.67
     Trafford
    -0.67
    Bene
    -0.65
    POSITIVE LOGITS
     Trig
    0.84
    Trig
    0.80
     Trich
    0.77
     Gon
    0.75
     Trilogy
    0.75
     TRIB
    0.74
     Trist
    0.73
     Larry
    0.72
     Trinidad
    0.71
     Guthrie
    0.70
    Act Density 1.326%

    No Known Activations