INDEX
    Explanations

    special markers or structural elements in the text

    New Auto-Interp
    Negative Logits
    //
    -0.89
    s
    -0.72
    Pyx
    -0.67
    e
    -0.61
    -0.60
    k
    -0.58
    er
    -0.57
     dan
    -0.57
     "
    -0.57
    т
    -0.56
    POSITIVE LOGITS
     مشين
    1.41
    __":
    
    1.28
    __':
    
    1.27
    --)
    
    1.24
    ")));
    
    1.15
     createState
    1.15
     nakalista
    1.13
    "){
    
    1.12
    ")){
    
    1.11
     }}$}
    1.11
    Act Density 0.029%

    No Known Activations