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

    Neuronpedia

    INDEX
    Explanations

    references to gender and its implications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Rüyada
    -0.54
    middels
    -0.44
    expandindo
    -0.43
     Initiate
    -0.41
     σή
    -0.41
    yonel
    -0.41
     صوتيه
    -0.41
     fotográfica
    -0.41
    posedge
    -0.40
     Objection
    -0.40
    POSITIVE LOGITS
     gender
    1.52
    Gender
    1.41
    gender
    1.35
     Gender
    1.35
     genders
    1.20
     sexes
    1.10
    GENDER
    1.09
     sex
    1.08
    Sex
    1.00
    性别
    0.94
    Act Density 0.296%

    No Known Activations