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

    Neuronpedia

    INDEX
    Explanations

    statements containing the word "feminist" with varying degrees of relevance and emphasis

    oai_token-act-pair · gpt-3.5-turbo

    references to feminism and feminists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sight
    -0.82
    laus
    -0.80
    INESS
    -0.74
    seeing
    -0.72
    mg
    -0.71
    acca
    -0.70
    gob
    -0.69
    Condition
    -0.69
    rip
    -0.68
    shape
    -0.68
    POSITIVE LOGITS
     feminists
    1.01
     feminist
    0.96
     feminism
    0.95
    galitarian
    0.85
     Feminist
    0.83
    azi
    0.80
     Equality
    0.71
     tracts
    0.71
     empowerment
    0.71
    andom
    0.70
    Act Density 0.016%

    No Known Activations