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

    Neuronpedia

    INDEX
    Explanations

    references to specific societies or groups, specifically comedy and feminist societies

    oai_token-act-pair · gpt-3.5-turbo

    references to feminist organizations or societies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Track
    -0.79
    ativity
    -0.78
    hei
    -0.69
    Mart
    -0.68
    Keefe
    -0.67
    alth
    -0.65
    essen
    -0.65
    uristic
    -0.64
    avery
    -0.64
    ulton
    -0.64
    POSITIVE LOGITS
    å¥
    0.74
    fed
    0.71
     ingred
    0.71
    使
    0.69
    代
    0.69
    éĹĺ
    0.66
    æĿ
    0.64
    è¡
    0.63
    jong
    0.63
    Ô
    0.62
    Act Density 0.000%

    No Known Activations