INDEX
    Explanations

    names of individuals, particularly those in sports contexts

    New Auto-Interp
    Negative Logits
     Normdatei
    -0.35
     fantasi
    -0.35
     neutr
    -0.34
    -0.33
    ாட
    -0.33
     her
    -0.32
     communicated
    -0.32
     tong
    -0.31
    ELE
    -0.30
     te
    -0.30
    POSITIVE LOGITS
     propOrder
    0.64
     BrowserModule
    0.63
     ***!
    0.59
    ьаж
    0.58
     يتيمه
    0.57
     Eilish
    0.57
    PYX
    0.56
    قایناقلار
    0.56
    MigrationBuilder
    0.55
    sonaro
    0.54
    Act Density 0.244%

    No Known Activations