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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    erest
    -0.79
    agascar
    -0.78
    ãĥ¯ãĥ³
    -0.77
    fman
    -0.76
    wikipedia
    -0.75
    psey
    -0.75
    development
    -0.72
    pread
    -0.72
    ĸļ
    -0.71
    hemat
    -0.70
    POSITIVE LOGITS
     snapping
    0.84
     adjourn
    0.69
     Canter
    0.68
     lif
    0.67
     jer
    0.66
     shattering
    0.65
     Walters
    0.64
     cooldown
    0.63
     recal
    0.63
     Casting
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.