INDEX
    Explanations

    prepositions and location words

    New Auto-Interp
    Negative Logits
     ویکی‌پدیای
    -0.69
     CreateTagHelper
    -0.66
     surla
    -0.63
    MigrationBuilder
    -0.63
    ArgsConstructor
    -0.61
    tvguidetime
    -0.61
     <<<<<<<<<<<<<<
    -0.59
    曖昧さ回避
    -0.59
    Manbalar
    -0.59
    المراجع
    -0.57
    POSITIVE LOGITS
     that
    0.62
    cydow
    0.55
    0.50
     somewhere
    0.49
     AppCompatTheme
    0.48
    Portail
    0.48
     Somewhere
    0.46
     Sachen
    0.45
     걸
    0.45
    Things
    0.45
    Act Density 0.005%

    No Known Activations