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

    Neuronpedia

    INDEX
    Explanations

    references to polls or surveys

    oai_token-act-pair · gpt-3.5-turbo

    elements related to polls or voting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ¥µ
    -0.72
    £ı
    -0.68
    urance
    -0.66
     atten
    -0.64
     baggage
    -0.63
    inary
    -0.62
     exting
    -0.62
    æ©Ł
    -0.61
    isol
    -0.61
    Alias
    -0.60
    POSITIVE LOGITS
     finalists
    1.07
     winner
    1.04
     contenders
    0.98
     contender
    0.96
     bidder
    0.92
    brainer
    0.90
    ecided
    0.89
     nominees
    0.88
    votes
    0.86
    Winner
    0.86
    Act Density 0.867%

    No Known Activations