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

    Neuronpedia

    INDEX
    Explanations

    references to political representatives and their party affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.03
    2:0.02
    3:0.04
    4:0.12
    5:0.11
    6:0.08
    7:0.03
    8:0.34
    9:0.05
    10:0.02
    11:0.02
    Negative Logits
    DragonMagazine
    -2.08
    ◼
    -1.81
     modem
    -1.75
    connection
    -1.75
     contain
    -1.70
     disinteg
    -1.69
    PsyNetMessage
    -1.67
    ionics
    -1.64
    biology
    -1.62
    istical
    -1.61
    POSITIVE LOGITS
     Vote
    2.00
     Votes
    1.99
    enegger
    1.96
     voted
    1.90
    ospons
    1.89
     DISTRICT
    1.79
     votes
    1.77
     Caucus
    1.73
    District
    1.72
     statewide
    1.70
    Act Density 0.026%

    No Known Activations