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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.07
    2:0.09
    3:0.10
    4:0.06
    5:0.07
    6:0.10
    7:0.08
    8:0.07
    9:0.09
    10:0.06
    11:0.09
    Negative Logits
     pic
    -1.90
    ..."
    -1.86
    weet
    -1.82
     Livingston
    -1.79
    dad
    -1.77
    gio
    -1.77
     footnote
    -1.75
     11
    -1.73
    aughter
    -1.72
    reath
    -1.70
    POSITIVE LOGITS
     裏�
    2.56
     defic
    2.23
     dissatisf
    2.20
    Sov
    2.17
     ingred
    2.09
    覚醒
    2.09
     reperc
    2.01
    ワン
    2.01
     preval
    1.99
     resil
    1.97
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.