INDEX
    Explanations

    expressions of appreciation or recognition from audiences

    New Auto-Interp
    Negative Logits
     estekak
    -0.58
    mbggenerated
    -0.50
    ADUATE
    -0.48
    ngt
    -0.48
    imuth
    -0.48
     (
    -0.47
    typename
    -0.47
    -0.46
    詳しくは
    -0.45
     входит
    -0.45
    POSITIVE LOGITS
    styleType
    0.70
     sarcas
    0.66
     scrolled
    0.64
     emoticon
    0.63
     emojis
    0.62
    κτηρισ
    0.61
    WithIOException
    0.59
     carats
    0.58
     favori
    0.57
    ően
    0.57
    Act Density 0.007%

    No Known Activations