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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Rampage
    -0.68
     Gins
    -0.66
    ellar
    -0.64
    oppable
    -0.63
     Mellon
    -0.63
     Phill
    -0.61
     Tuls
    -0.61
    akedown
    -0.61
    withstanding
    -0.60
     Gors
    -0.60
    POSITIVE LOGITS
    sc
    0.97
    esy
    0.85
    scribe
    0.77
    stem
    0.75
    lass
    0.74
    ften
    0.72
    tes
    0.71
    aul
    0.71
    helps
    0.70
     Logged
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.