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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     equivalent
    -0.71
     pse
    -0.70
     endowed
    -0.69
     transfer
    -0.67
     ming
    -0.66
     fitted
    -0.65
     intercept
    -0.65
     glide
    -0.64
     kiss
    -0.62
     aide
    -0.61
    POSITIVE LOGITS
    LC
    0.76
     Abbey
    0.75
    ãĤ¤ãĥĪ
    0.74
    è¦ļéĨĴ
    0.74
    .,"
    0.71
    ðŁĺ
    0.70
    fn
    0.70
    ETA
    0.70
    FD
    0.69
    foundland
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.