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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.05
    2:0.09
    3:0.09
    4:0.08
    5:0.08
    6:0.07
    7:0.08
    8:0.07
    9:0.07
    10:0.08
    11:0.08
    Negative Logits
     editions
    -1.71
    iability
    -1.68
     breeds
    -1.68
    arnaev
    -1.63
    rupulous
    -1.58
    oufl
    -1.57
    arers
    -1.57
     corrid
    -1.53
     passports
    -1.53
     stockp
    -1.51
    POSITIVE LOGITS
    _.
    2.23
    Construction
    1.76
    ().
    1.63
     Explain
    1.60
    >.
    1.58
    Grant
    1.58
    {
    1.58
    >(
    1.58
    twitter
    1.57
     Called
    1.56
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.