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

    Neuronpedia

    INDEX
    Explanations

    text related to voting or polls

    oai_token-act-pair · gpt-3.5-turbo

    terms related to voting and polling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imilar
    -0.71
    ofi
    -0.71
    ptoms
    -0.71
    ifax
    -0.70
     Afric
    -0.69
     Kut
    -0.68
     tremend
    -0.67
    peria
    -0.67
     Morton
    -0.67
    quite
    -0.67
    POSITIVE LOGITS
     polls
    0.84
     cast
    0.84
     unanimously
    0.82
    board
    0.80
    ndum
    0.80
     approving
    0.79
    bot
    0.79
     votes
    0.74
     ballots
    0.72
     wisely
    0.70
    Act Density 0.059%

    No Known Activations