INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    zeros
    -0.09
    Form
    -0.08
    hydr
    -0.08
    huk
    -0.08
     dehydr
    -0.08
    _form
    -0.08
    	form
    -0.07
     Form
    -0.07
     FORM
    -0.07
     bhr
    -0.07
    POSITIVE LOGITS
     lav
    0.08
     mở
    0.07
     oraz
    0.07
     truly
    0.07
     materiali
    0.07
    lav
    0.07
     ไป
    0.07
     Ø
    0.07
    Themes
    0.07
     material
    0.07
    Act Density 0.249%

    No Known Activations