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

    Neuronpedia

    INDEX
    Explanations

    references to gender, particularly male and female

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    men
    -0.94
    man
    -0.89
    onViewCreated
    -0.72
    Zin
    -0.69
    MEN
    -0.69
    obatan
    -0.69
    WebServlet
    -0.68
    ly
    -0.67
     Notion
    -0.65
     Zat
    -0.62
    POSITIVE LOGITS
     MALE
    1.01
     Male
    0.99
    MALE
    0.98
     Males
    0.94
     males
    0.93
     Females
    0.92
    emale
    0.90
    Males
    0.90
     mâle
    0.89
    Male
    0.88
    Act Density 0.032%

    No Known Activations