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

    Neuronpedia

    INDEX
    Explanations

    terms related to politics

    oai_token-act-pair · gpt-3.5-turbo

    references to politics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FIG
    -0.87
     Item
    -0.69
    uin
    -0.66
    ii
    -0.66
    heim
    -0.65
    Figure
    -0.65
     Instruct
    -0.65
    Amount
    -0.64
    isode
    -0.63
     Additional
    -0.62
    POSITIVE LOGITS
     politics
    3.71
     Politics
    2.56
    politics
    2.53
    Politics
    2.23
     political
    1.89
    political
    1.80
     politic
    1.73
    polit
    1.71
     politicians
    1.68
    Political
    1.65
    Act Density 0.017%

    No Known Activations