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

    Neuronpedia

    INDEX
    Explanations

    mentions of political affiliations, specifically with an emphasis on Democratic party members

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Democrat" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urious
    -0.79
    utils
    -0.72
    iffs
    -0.70
    obyl
    -0.70
    prototype
    -0.70
    iddles
    -0.70
    illin
    -0.70
    ysics
    -0.66
    ador
    -0.65
    weather
    -0.65
    POSITIVE LOGITS
     Party
    0.87
    naissance
    0.83
    izable
    0.76
    hood
    0.75
     stronghold
    0.75
     caucuses
    0.75
     politician
    0.73
     nominee
    0.71
     voter
    0.69
     strongh
    0.69
    Act Density 0.033%

    No Known Activations