INDEX
    Explanations

    instances of vocal expressions of emotion, particularly shouting and calling

    New Auto-Interp
    Negative Logits
    zik
    -0.17
    imers
    -0.15
    etta
    -0.15
    Ñħод
    -0.14
    ials
    -0.14
    cala
    -0.14
    å±Ģ
    -0.14
    ope
    -0.14
     Dans
    -0.14
    ÐľÐŀ
    -0.14
    POSITIVE LOGITS
     Spare
    0.14
    ril
    0.14
    deer
    0.14
     Robbins
    0.14
    ValueCollection
    0.13
     TSRMLS
    0.13
    æľĭ
    0.13
    ë
    0.13
     spare
    0.13
    çīĮ
    0.13
    Act Density 0.062%

    No Known Activations