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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     exha
    -0.72
     concentrated
    -0.66
     sag
    -0.65
     ability
    -0.63
     casc
    -0.62
    ched
    -0.60
    gal
    -0.59
     Bund
    -0.59
    opathic
    -0.59
     rendered
    -0.58
    POSITIVE LOGITS
    guard
    0.77
    olson
    0.75
    wright
    0.74
    hran
    0.71
    anson
    0.70
    sein
    0.70
    Marx
    0.66
    icket
    0.65
    mist
    0.65
    ickets
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.