INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Betting
    -0.08
    Alles
    -0.08
     Pacific
    -0.08
    Universe
    -0.08
    Pues
    -0.08
     Same
    -0.08
    ुओ
    -0.07
     ^^
    -0.07
     slender
    -0.07
    овало
    -0.07
    POSITIVE LOGITS
     dull
    0.12
     sluggish
    0.11
    0.08
    embers
    0.08
    0.08
     quieter
    0.08
    0.08
     absorbed
    0.08
     туп
    0.08
     hush
    0.07
    Act Density 0.009%

    No Known Activations