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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    baugh
    -0.79
    anol
    -0.72
    ixties
    -0.72
    pez
    -0.70
    ktop
    -0.68
    lying
    -0.66
    phis
    -0.65
    itri
    -0.63
    footed
    -0.60
    ocene
    -0.60
    POSITIVE LOGITS
    ournament
    0.72
     Ultimate
    0.67
    erers
    0.67
     Gears
    0.65
    ãĥĸ
    0.61
     bund
    0.59
     Vi
    0.59
     interchangeable
    0.59
     alias
    0.59
     Rack
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.