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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.06
    2:0.08
    3:0.08
    4:0.08
    5:0.07
    6:0.08
    7:0.07
    8:0.08
    9:0.07
    10:0.09
    11:0.09
    Negative Logits
    zos
    -1.72
    FREE
    -1.71
    neau
    -1.66
    BI
    -1.63
    raped
    -1.61
    oult
    -1.60
    フォ
    -1.59
    hur
    -1.59
    Free
    -1.59
    USER
    -1.58
    POSITIVE LOGITS
     conclud
    1.74
     probabilities
    1.69
     fractions
    1.58
     Azerb
    1.52
    ijuana
    1.50
     Tsukuyomi
    1.50
     Classification
    1.50
     retrospect
    1.48
     Mons
    1.48
     probability
    1.48
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.