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

    Neuronpedia

    INDEX
    Explanations

    references to gender and female-specific topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    insics
    -0.60
     Infórmanos
    -0.56
     AssemblyCulture
    -0.52
    LayoutStyle
    -0.49
     Sünde
    -0.49
    dAtA
    -0.48
    }();
    -0.48
     htons
    -0.47
    *}[
    -0.47
     EconPapers
    -0.47
    POSITIVE LOGITS
     female
    4.32
     Female
    3.99
    Female
    3.92
    female
    3.86
     FEMALE
    3.63
     male
    3.19
    FEMALE
    3.15
     females
    3.10
    Male
    2.85
     Females
    2.82
    Act Density 0.099%

    No Known Activations