INDEX
    Explanations

    exclamatory punctuation and expressions of strong emotion

    New Auto-Interp
    Negative Logits
    wares
    -0.16
    Ñĥнок
    -0.15
    peare
    -0.15
     nÃło
    -0.15
    yr
    -0.15
    hape
    -0.14
    ful
    -0.14
    aken
    -0.14
       
    -0.13
    _FN
    -0.13
    POSITIVE LOGITS
    estion
    0.15
    ieme
    0.14
    oker
    0.14
    526
    0.14
    laz
    0.14
    raki
    0.13
    íķ©
    0.13
    nem
    0.13
    ptype
    0.13
    etween
    0.13
    Act Density 0.114%

    No Known Activations