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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    loe
    -0.76
     Athletic
    -0.69
    erry
    -0.65
    ullivan
    -0.63
    raine
    -0.63
     Maduro
    -0.62
    ERN
    -0.59
    ovsky
    -0.58
    redo
    -0.58
    saw
    -0.58
    POSITIVE LOGITS
    BILITIES
    0.92
    codes
    0.75
    FactoryReloaded
    0.70
     CASE
    0.69
    mination
    0.68
    abilities
    0.67
    holes
    0.65
    Available
    0.64
    parts
    0.63
     Mehran
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.