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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ãĥ´
    -0.80
    âĸ¬âĸ¬
    -0.76
     Blasio
    -0.73
    ICA
    -0.70
    Zip
    -0.69
    eden
    -0.68
    isSpecialOrderable
    -0.68
    ROR
    -0.68
    racial
    -0.68
    ãĥį
    -0.68
    POSITIVE LOGITS
     dishon
    0.81
     unsu
    0.69
     guilty
    0.67
    onite
    0.65
    tery
    0.65
     culp
    0.65
     276
    0.64
    attery
    0.63
     worthless
    0.62
    rued
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.