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

    Neuronpedia

    INDEX
    Explanations

    statistical data and political candidate details

    oai_token-act-pair · gpt-3.5-turbo

    percentages associated with political polling data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    seless
    -0.73
     treat
    -0.68
    unct
    -0.64
     lineback
    -0.64
     subclass
    -0.63
     Regulations
    -0.62
     supplement
    -0.62
     Treat
    -0.62
     landlord
    -0.60
     supra
    -0.60
    POSITIVE LOGITS
     votes
    1.18
    votes
    1.13
     polled
    0.97
     turnout
    0.97
     electoral
    0.94
     polls
    0.93
     vote
    0.92
     ballots
    0.91
     voters
    0.90
     polling
    0.90
    Act Density 0.157%

    No Known Activations