INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ovima
    -0.09
     siebie
    -0.08
    (tc
    -0.08
     TK
    -0.08
     wn
    -0.08
     Tmin
    -0.08
    amuzi
    -0.07
     losers
    -0.07
     Kona
    -0.07
     wb
    -0.07
    POSITIVE LOGITS
     coat
    0.09
    coat
    0.08
     coats
    0.08
     taxed
    0.07
     crisp
    0.07
     brush
    0.07
     चम
    0.07
     coloration
    0.07
     лап
    0.07
     textura
    0.07
    Act Density 0.006%

    No Known Activations