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

    Neuronpedia

    INDEX
    Explanations

    references to female individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "girl."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aeda
    -0.86
    CAST
    -0.80
    rehend
    -0.72
    henko
    -0.70
     destro
    -0.69
    PDATE
    -0.69
    aution
    -0.68
    aukee
    -0.68
    odcast
    -0.68
    insula
    -0.68
    POSITIVE LOGITS
     Scouts
    1.04
     girls
    0.87
    hood
    0.86
    ish
    0.85
    girl
    0.82
    ishly
    0.82
     girl
    0.81
    folk
    0.80
     panties
    0.79
    girls
    0.79
    Act Density 0.020%

    No Known Activations