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

    Neuronpedia

    INDEX
    Explanations

    elements related to personal identification and integrity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.03
    2:0.07
    3:0.05
    4:0.05
    5:0.03
    6:0.27
    7:0.04
    8:0.07
    9:0.18
    10:0.02
    11:0.05
    Negative Logits
     plank
    -3.79
     commons
    -3.55
     Pyth
    -3.52
    ysical
    -3.48
     syll
    -3.34
     compe
    -3.23
     Synd
    -3.17
    ython
    -3.14
    yrim
    -3.12
    cyl
    -3.12
    POSITIVE LOGITS
     Hogan
    11.78
     Gou
    5.50
     Hulk
    5.37
     Hog
    5.20
     Gawker
    5.15
    ogan
    4.90
     Higgins
    4.73
     Jindal
    4.43
     Toledo
    4.19
    Hart
    4.18
    Act Density 0.002%

    No Known Activations