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

    Neuronpedia

    INDEX
    Explanations

    references to women

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "woman" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ypes
    -0.99
    raltar
    -0.82
    kefeller
    -0.82
     Flavoring
    -0.77
    vernment
    -0.76
    ernels
    -0.76
    ype
    -0.76
    UFF
    -0.75
    aucuses
    -0.74
    emetery
    -0.72
    POSITIVE LOGITS
    izer
    1.22
    hood
    1.09
     herself
    1.09
    pher
    1.00
    folk
    0.95
     vagina
    0.93
    cule
    0.92
    izers
    0.90
     menstru
    0.89
     Louise
    0.89
    Act Density 0.059%

    No Known Activations