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

    Neuronpedia

    INDEX
    Explanations

    references to mysterious entities or situations, particularly those involving individuals or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.04
    2:0.05
    3:0.04
    4:0.02
    5:0.05
    6:0.10
    7:0.15
    8:0.07
    9:0.03
    10:0.08
    11:0.29
    Negative Logits
    エル
    -1.33
    ullivan
    -1.31
    amation
    -1.28
     Liberties
    -1.21
     GOODMAN
    -1.20
     Recommend
    -1.18
     Debate
    -1.16
    cipled
    -1.15
    cknowled
    -1.13
     )]
    -1.11
    POSITIVE LOGITS
     whispers
    1.20
     demons
    1.13
     mysterious
    1.10
     lurking
    1.08
     enigmatic
    1.03
     bandits
    1.03
     quirks
    1.03
     shrouded
    1.03
     sculptures
    1.02
     Pirates
    1.02
    Act Density 0.015%

    No Known Activations