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

    Neuronpedia

    INDEX
    Explanations

    references to women and their roles or characteristics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.77
    -0.77
     ModelExpression
    -0.74
     mergeFrom
    -0.72
    BeginContext
    -0.71
    ControllerAdvice
    -0.70
    thâu
    -0.69
    ureka
    -0.65
     nahilalakip
    -0.64
     HttpNotFound
    -0.62
    POSITIVE LOGITS
     woman
    0.77
     Woman
    0.72
     broker
    0.70
    ]=="
    0.67
    Woman
    0.63
     humans
    0.63
     WOMAN
    0.62
     Jérusalem
    0.61
     Broker
    0.61
     humankind
    0.59
    Act Density 0.081%

    No Known Activations