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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political voting behavior

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "voted for."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illin
    -0.97
    Scope
    -0.87
    ngth
    -0.86
    mone
    -0.82
    catentry
    -0.80
    urst
    -0.79
    ofi
    -0.78
    Warning
    -0.76
    urgical
    -0.76
    clair
    -0.75
    POSITIVE LOGITS
     reelection
    0.96
     politicians
    0.86
     captcha
    0.84
     Hillary
    0.84
     starters
    0.83
     votes
    0.83
     whichever
    0.82
     ballot
    0.79
     elected
    0.76
     voting
    0.75
    Act Density 0.047%

    No Known Activations