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

    Neuronpedia

    INDEX
    Explanations

    references to voting behavior

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "vote for" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -1.03
    illin
    -0.87
    mone
    -0.86
    clair
    -0.81
    urst
    -0.80
    Scope
    -0.78
    catentry
    -0.74
    urgical
    -0.72
    icult
    -0.72
    trace
    -0.71
    POSITIVE LOGITS
     reelection
    0.89
     captcha
    0.87
     whichever
    0.85
    geries
    0.81
     votes
    0.80
     independence
    0.78
     Hillary
    0.78
     politicians
    0.78
     whatever
    0.77
     electing
    0.76
    Act Density 0.055%

    No Known Activations