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

    Neuronpedia

    INDEX
    Explanations

    mentions of actions or processes related to voting and public decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.02
    2:0.12
    3:0.06
    4:0.11
    5:0.02
    6:0.06
    7:0.38
    8:0.02
    9:0.02
    10:0.06
    11:0.07
    Negative Logits
    CHAT
    -1.79
    xp
    -1.56
    lance
    -1.53
    ect
    -1.51
    sth
    -1.47
    ech
    -1.46
    JD
    -1.45
    adders
    -1.41
    ois
    -1.40
    orer
    -1.39
    POSITIVE LOGITS
     jeopardy
    1.70
     Tsukuyomi
    1.67
     boarding
    1.60
     Metatron
    1.46
     Vengeance
    1.42
     disposable
    1.40
     Toro
    1.39
     stead
    1.38
     bin
    1.37
     discredit
    1.34
    Act Density 0.049%

    No Known Activations