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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    orry
    -0.71
    glass
    -0.65
    isers
    -0.65
    izers
    -0.65
    ARY
    -0.65
    ivan
    -0.60
     Draper
    -0.60
    hurst
    -0.60
    ?".
    -0.59
    ?).
    -0.59
    POSITIVE LOGITS
    AppData
    0.75
    iatus
    0.74
     Lanka
    0.72
     srf
    0.71
    ulse
    0.68
    ugal
    0.67
    Synopsis
    0.67
    ftime
    0.65
    aah
    0.63
     occas
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.