INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     parish
    -0.07
    ürn
    -0.06
    57
    -0.06
       	
    -0.06
    -grow
    -0.06
     neut
    -0.06
    point
    -0.06
    -open
    -0.06
    just
    -0.06
    _pag
    -0.06
    POSITIVE LOGITS
     э
    0.15
     Э
    0.12
    Э
    0.12
     بإ
    0.08
    -E
    0.08
    الإ
    0.08
    э
    0.07
     Emergency
    0.07
     ini
    0.07
    0.07
    Act Density 0.008%

    No Known Activations