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

    Neuronpedia

    INDEX
    Explanations

    contexts related to disasters or catastrophic events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.08
    3:0.09
    4:0.16
    5:0.03
    6:0.08
    7:0.30
    8:0.03
    9:0.03
    10:0.06
    11:0.05
    Negative Logits
    eret
    -1.97
    chnology
    -1.80
    iera
    -1.76
    aiden
    -1.74
    older
    -1.73
    ibrary
    -1.66
    isSpecialOrderable
    -1.66
    essional
    -1.64
    版
    -1.63
    escription
    -1.62
    POSITIVE LOGITS
     havoc
    1.87
     vib
    1.80
     glitches
    1.74
     inequ
    1.69
     boredom
    1.66
     Rebell
    1.63
     contradictions
    1.61
     rud
    1.57
     disappoint
    1.56
     jealousy
    1.48
    Act Density 0.000%

    No Known Activations