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

    Neuronpedia

    INDEX
    Explanations

    words related to males or masculinity

    oai_token-act-pair · gpt-3.5-turbo

    references to male entities or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etsk
    -0.79
     GOODMAN
    -0.79
    leans
    -0.75
    krit
    -0.72
    today
    -0.71
    adr
    -0.70
    lov
    -0.70
    anwhile
    -0.69
    rep
    -0.67
    bleacher
    -0.66
    POSITIVE LOGITS
    volent
    1.70
     ejac
    0.92
     genital
    0.90
    vol
    0.87
     Male
    0.83
     male
    0.82
     sexuality
    0.81
     infertility
    0.80
     circumcision
    0.76
     males
    0.76
    Act Density 0.011%

    No Known Activations