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

    Neuronpedia

    INDEX
    Explanations

    references to women or events related to women

    oai_token-act-pair · gpt-3.5-turbo

    references to women and women's events or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quo
    -0.74
     retri
    -0.72
     ram
    -0.70
     tune
    -0.69
    upon
    -0.69
     earth
    -0.67
    leon
    -0.65
     jurisdiction
    -0.63
     replay
    -0.63
     nig
    -0.62
    POSITIVE LOGITS
    Works
    0.99
     Woman
    0.95
     Women
    0.95
     Programs
    0.91
     Rights
    0.86
     Writers
    0.85
     Violence
    0.85
     Services
    0.85
    ysc
    0.84
     Matters
    0.83
    Act Density 0.037%

    No Known Activations