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

    Neuronpedia

    INDEX
    Explanations

    references to familial relationships, particularly involving wives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Avalon
    -0.79
     Doodle
    -0.78
     Mako
    -0.77
     poc
    -0.70
    Aval
    -0.69
     Calla
    -0.69
     Uru
    -0.67
    рог
    -0.65
    abar
    -0.65
     Mov
    -0.65
    POSITIVE LOGITS
     wives
    1.18
     wife
    1.17
     WIFE
    1.12
     moglie
    1.07
    wife
    1.05
    Wife
    1.02
     istri
    0.99
     Wife
    0.99
     marito
    0.93
     esposa
    0.92
    Act Density 0.037%

    No Known Activations