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

    Neuronpedia

    INDEX
    Explanations

    phrases related to individuals or specific people

    oai_token-act-pair · gpt-3.5-turbo

    references to significant individuals or public figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    selves
    -0.78
     husbands
    -0.77
    alities
    -0.69
    ascript
    -0.66
     miscarriage
    -0.66
    acas
    -0.64
    lishes
    -0.64
     ¶
    -0.64
     mothers
    -0.60
     moms
    -0.59
    POSITIVE LOGITS
     himself
    0.96
     personally
    0.73
    sov
    0.72
     Himself
    0.71
     Emin
    0.70
    ithe
    0.69
     Rai
    0.66
    redd
    0.66
    perse
    0.66
    chenko
    0.65
    Act Density 1.464%

    No Known Activations