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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    prominent individuals and references to champagne

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kefeller
    -0.83
    oxin
    -0.82
    heed
    -0.80
    essential
    -0.73
    uran
    -0.73
    yip
    -0.73
    uador
    -0.71
    itude
    -0.70
    anmar
    -0.68
    MpServer
    -0.68
    POSITIVE LOGITS
    furt
    0.94
    ··
    0.75
    mast
    0.72
    bach
    0.71
    cision
    0.68
    clude
    0.68
     Mü
    0.67
    cised
    0.66
     Lutheran
    0.66
     SV
    0.66
    Act Density 0.024%

    No Known Activations