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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Roy
    -0.70
    hurst
    -0.69
    Brook
    -0.68
    Cole
    -0.67
    ĸļ
    -0.66
     Drawn
    -0.63
     Inspect
    -0.61
     Kendall
    -0.60
    ENN
    -0.60
     Built
    -0.60
    POSITIVE LOGITS
    race
    0.73
    issan
    0.71
    ounces
    0.71
    umph
    0.69
    ettel
    0.69
    ema
    0.67
    Reloaded
    0.65
     holiday
    0.65
    PsyNetMessage
    0.64
    odus
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.