INDEX
    Explanations

    say "equal sign"

    New Auto-Interp
    Negative Logits
     '
    -0.57
     ‘
    -0.54
     :
    -0.49
    ANDE
    -0.49
     «
    -0.42
     "
    -0.41
     suất
    -0.41
     med
    -0.40
    :“
    -0.38
    figura
    -0.38
    POSITIVE LOGITS
    =-
    0.81
    =/
    0.77
    =$
    0.77
    =!
    0.77
    =%
    0.76
    =
    0.76
    =_
    0.71
    ={
    0.70
    =.
    0.70
    CloseOperation
    0.69
    Act Density 0.021%

    No Known Activations