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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Alvin
    -0.84
    Classic
    -0.71
    clusion
    -0.71
     Coffin
    -0.70
     Ake
    -0.70
    gee
    -0.69
    peak
    -0.69
     Clothing
    -0.68
    athlon
    -0.65
    Johnny
    -0.64
    POSITIVE LOGITS
    itted
    0.69
    brance
    0.67
     showc
    0.67
    oresc
    0.66
    [_
    0.65
     stead
    0.65
     compet
    0.65
    itized
    0.62
    pher
    0.62
    ARI
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.