INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    стр
    -0.08
    (r
    -0.07
     استر
    -0.07
    @
    -0.06
     Yok
    -0.06
    nech
    -0.06
     dessert
    -0.06
    =en
    -0.06
    -0.06
    زد
    -0.06
    POSITIVE LOGITS
    260
    0.07
     odpověd
    0.06
     Real
    0.06
     supernatural
    0.06
    0.06
    das
    0.06
    	NdrFcShort
    0.06
    Permanent
    0.06
    loat
    0.06
     بت
    0.06
    Act Density 0.100%

    No Known Activations