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

    Neuronpedia

    INDEX
    Explanations

    terms related to calamities or widespread issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to plagues or widespread diseases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aunder
    -0.88
    seys
    -0.83
    earchers
    -0.78
    atican
    -0.75
    ially
    -0.75
    externalActionCode
    -0.73
    udeau
    -0.71
    natureconservancy
    -0.70
    iosity
    -0.69
    ial
    -0.69
    POSITIVE LOGITS
     plague
    0.94
     Plague
    0.82
    velt
    0.69
    lust
    0.68
    die
    0.66
     poisoning
    0.65
    lords
    0.65
     Legion
    0.64
    icter
    0.63
    bug
    0.63
    Act Density 0.044%

    No Known Activations