INDEX
    Explanations

    references to artistic or creative works

    Follows passive voice verbs

    New Auto-Interp
    Negative Logits
    }{*}{
    -0.47
    aimana
    -0.46
     angekommen
    -0.43
    ]]:
    -0.43
    ChildScrollView
    -0.43
     miniaturka
    -0.43
    IntoConstraints
    -0.43
    seamnă
    -0.43
    ligators
    -0.43
    )]:
    -0.42
    POSITIVE LOGITS
     oleh
    0.65
     by
    0.61
     توسط
    0.58
    0.58
     بواسطة
    0.46
     milik
    0.43
    ffilm
    0.43
     courtesy
    0.42
     conducted
    0.42
    oleh
    0.41
    Act Density 0.711%

    No Known Activations