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

    Neuronpedia

    INDEX
    Explanations

    phrases related to voting processes, such as absentee ballots and ballot counting

    oai_token-act-pair · gpt-3.5-turbo

    references to ballots in the context of voting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obar
    -0.77
    TIT
    -0.74
    Relations
    -0.71
    Sym
    -0.70
    CHR
    -0.69
    vern
    -0.69
    vid
    -0.68
    thy
    -0.66
    eland
    -0.66
    ty
    -0.65
    POSITIVE LOGITS
     ballots
    1.48
     ballot
    1.07
     Compass
    0.93
     votes
    0.92
     canv
    0.89
     voting
    0.88
     Vote
    0.84
     Votes
    0.84
    Vote
    0.83
    avorite
    0.81
    Act Density 0.008%

    No Known Activations