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

    Neuronpedia

    INDEX
    Explanations

    references to feminist concepts or feminism

    oai_token-act-pair · gpt-3.5-turbo

    terms related to feminism and feminist discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    laus
    -0.83
    INESS
    -0.74
    acca
    -0.71
    --------------------
    -0.69
    Lago
    -0.66
    rip
    -0.65
    rive
    -0.65
    DOWN
    -0.65
    worldly
    -0.64
     Solitaire
    -0.64
    POSITIVE LOGITS
    azi
    0.87
     feminist
    0.86
    andom
    0.84
     feminism
    0.80
     feminists
    0.80
     Feminist
    0.79
    osphere
    0.72
     panties
    0.71
     anthology
    0.70
    initions
    0.69
    Act Density 0.027%

    No Known Activations