INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Leidenschaft
    -0.08
     passion
    -0.08
     Light
    -0.08
     уст
    -0.07
     obsolete
    -0.07
     бала
    -0.07
    zca
    -0.07
     passie
    -0.07
     Gez
    -0.07
     pony
    -0.07
    POSITIVE LOGITS
    通常
    0.09
    에서는
    0.08
     complications
    0.08
     sieht
    0.08
     teknik
    0.08
     일반
    0.08
    0.08
    flutter
    0.07
     fashion
    0.07
    Typically
    0.07
    Act Density 0.056%

    No Known Activations