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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to political affiliation, specifically indicating an association with the Democratic party

    oai_token-act-pair · gpt-3.5-turbo

    references to the Democratic Party

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obyl
    -0.82
    iddles
    -0.78
    urious
    -0.76
    weather
    -0.75
    illin
    -0.75
    prototype
    -0.74
    iffs
    -0.72
    utils
    -0.72
    laus
    -0.69
    ansen
    -0.68
    POSITIVE LOGITS
    naissance
    0.78
     Party
    0.76
    ization
    0.72
    izable
    0.71
     politician
    0.69
     operative
    0.69
     stronghold
    0.67
    hood
    0.66
    ification
    0.66
     standby
    0.64
    Act Density 0.015%

    No Known Activations