INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    gast
    -0.08
     tummy
    -0.08
    Rose
    -0.08
    Gast
    -0.08
    Medium
    -0.08
    -gh
    -0.08
    Rome
    -0.07
    Small
    -0.07
    Excluded
    -0.07
    Wide
    -0.07
    POSITIVE LOGITS
     автоматически
    0.08
     пер
    0.08
    0.08
     Manche
    0.08
     Prints
    0.08
     automatisch
    0.08
     manche
    0.08
     үл
    0.08
     Seit
    0.08
     ие
    0.08
    Act Density 0.002%

    No Known Activations