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

    Neuronpedia

    INDEX
    Explanations

    identifiers related to people, particularly in professional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.15
    2:0.02
    3:0.07
    4:0.03
    5:0.09
    6:0.11
    7:0.17
    8:0.04
    9:0.03
    10:0.02
    11:0.18
    Negative Logits
     Jackets
    -2.42
    worms
    -2.24
    ESE
    -2.24
     Chimera
    -2.20
     Tigers
    -2.19
     Raptors
    -2.09
    Match
    -2.06
     Coyotes
    -2.05
     Fnatic
    -2.04
    DX
    -2.03
    POSITIVE LOGITS
     Barack
    2.92
     Dianne
    2.87
     Tuls
    2.86
     Barbara
    2.76
     Bill
    2.75
    20439
    2.74
     Lyndon
    2.74
     Nancy
    2.73
     Martha
    2.68
     Susan
    2.67
    Act Density 0.000%

    No Known Activations