INDEX
    Explanations

    Medical studies and hormones

    New Auto-Interp
    Negative Logits
     BoxFit
    -0.89
    EndInit
    -0.86
    AddTagHelper
    -0.84
    BeginInit
    -0.83
     BoxDecoration
    -0.78
    DockStyle
    -0.77
    LookAnd
    -0.75
    IsContent
    -0.75
     <<<<<<<<<<<<<<
    -0.75
     مشين
    -0.75
    POSITIVE LOGITS
     with
    0.46
     pa
    0.45
    <bos>
    0.42
     dedi
    0.41
     younger
    0.40
    बार
    0.40
    ाई
    0.36
    i
    0.36
     у
    0.35
     suffering
    0.35
    Act Density 0.350%

    No Known Activations