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

    Neuronpedia

    INDEX
    Explanations

    words related to gender-specific body parts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to genitalia and genital-related medical procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GOODMAN
    -0.90
    EFF
    -0.80
    MER
    -0.73
    ETH
    -0.72
    resp
    -0.72
     Strong
    -0.72
    AR
    -0.69
     Ole
    -0.67
    quickShipAvailable
    -0.67
    Breaking
    -0.67
    POSITIVE LOGITS
     genital
    1.31
     herpes
    1.00
     genitals
    0.99
     organs
    0.84
    cised
    0.83
    inant
    0.80
     wart
    0.80
    ia
    0.78
     foreskin
    0.78
     stalls
    0.78
    Act Density 0.006%

    No Known Activations