INDEX
    Explanations

    watching/viewing

    New Auto-Interp
    Negative Logits
     screen
    -0.72
    s
    -0.68
     screening
    -0.63
    screen
    -0.60
    e
    -0.57
    screening
    -0.56
    ی
    -0.56
    ه
    -0.55
    yte
    -0.52
    soft
    -0.51
    POSITIVE LOGITS
     ویکی‌پدی
    0.65
     للاسماء
    0.65
     Anfitrión
    0.65
    tvguidetime
    0.65
    RepeatedField
    0.65
    ParallelGroup
    0.65
     Chwiliwch
    0.64
    parsedMessage
    0.64
    ]")]
    0.63
    matchCondition
    0.61
    Act Density 0.029%

    No Known Activations