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

    Neuronpedia

    INDEX
    Explanations

    mentions of men and gender-related issues

    oai_token-act-pair · gpt-3.5-turbo

    references to men and gender-related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IVERS
    -0.85
    ITS
    -0.74
    Assembly
    -0.74
     Manufacturer
    -0.73
    UFF
    -0.70
    Deal
    -0.69
    mble
    -0.65
    ylum
    -0.65
    arthed
    -0.63
    UGE
    -0.63
    POSITIVE LOGITS
    volent
    1.24
    opausal
    1.16
     ejac
    1.07
    folk
    0.93
    stru
    0.92
     genitals
    0.89
    handled
    0.84
     marrying
    0.83
     grooming
    0.83
     genital
    0.81
    Act Density 0.118%

    No Known Activations