INDEX
    Explanations

    the presence of the word "any."

    New Auto-Interp
    Negative Logits
    lüğ
    -0.65
    gule
    -0.63
    stdc
    -0.61
    óta
    -0.60
    lıyor
    -0.60
    ation
    -0.58
    Griffin
    -0.56
    slideUp
    -0.49
     agrade
    -0.49
     referrerpolicy
    -0.48
    POSITIVE LOGITS
     Any
    1.16
     ANY
    1.11
     any
    1.10
    Any
    1.07
    ANY
    1.02
     Anya
    1.00
     Qualquer
    0.95
    any
    0.95
    antMatchers
    0.94
    glicher
    0.87
    Act Density 0.100%

    No Known Activations