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

    Neuronpedia

    INDEX
    Explanations

    references to feminism and its criticisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.12
    1:0.02
    2:0.17
    3:0.09
    4:0.03
    5:0.11
    6:0.07
    7:0.07
    8:0.13
    9:0.08
    10:0.03
    11:0.02
    Negative Logits
    Poké
    -3.19
     Ulster
    -2.88
    NAS
    -2.83
     Newark
    -2.72
     Delaware
    -2.70
     Antar
    -2.70
    Reviewer
    -2.70
    phabet
    -2.70
     Tourism
    -2.69
     Wilmington
    -2.67
    POSITIVE LOGITS
     feminism
    8.16
     feminists
    8.12
     feminist
    7.74
    femin
    7.67
     Femin
    7.62
     Feminist
    7.53
     femin
    6.46
     patriarchy
    6.03
     sexist
    5.86
     sexism
    5.78
    Act Density 0.058%

    No Known Activations