INDEX
    Explanations

    emotional expressions and reactions

    New Auto-Interp
    Negative Logits
    TagMode
    -0.66
    }}}}
    -0.65
    }}},
    -0.61
    ')),
    -0.61
    httphttps
    -0.58
    "}"
    -0.57
     {}));
    -0.57
    ")),
    -0.57
    )>=
    -0.56
    eniu
    -0.56
    POSITIVE LOGITS
     nahilalakip
    0.95
    Amicalement
    0.87
     Chwiliwch
    0.82
    TargetException
    0.73
    GraphicsUnit
    0.72
     محفوظة
    0.69
    abestanden
    0.68
     ویکی‌پدیای
    0.66
    اریخ
    0.66
    באנגלית
    0.62
    Act Density 0.282%

    No Known Activations