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

    Neuronpedia

    INDEX
    Explanations

    numerical data such as percentages, votes, and leads in political contexts

    oai_token-act-pair · gpt-3.5-turbo

    statistical data related to political polling and election results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obyl
    -0.73
     restruct
    -0.72
     liner
    -0.71
     Sapp
    -0.68
     overload
    -0.67
     Collective
    -0.64
    artifacts
    -0.63
     Arbit
    -0.63
    CHAPTER
    -0.62
     explorers
    -0.62
    POSITIVE LOGITS
     polling
    0.97
     margin
    0.96
     undecided
    0.90
    til
    0.88
    election
    0.88
     polls
    0.87
    poll
    0.85
     Gillespie
    0.83
    vati
    0.83
    realDonaldTrump
    0.83
    Act Density 0.302%

    No Known Activations