INDEX
    Explanations

    punctuation and structural elements in written text

    New Auto-Interp
    Negative Logits
    telegram
    -0.15
    ONUS
    -0.14
    atoi
    -0.14
    é½
    -0.14
    Ñģлов
    -0.14
    abcdefghijkl
    -0.14
    alse
    -0.13
    abcdefghijklmnop
    -0.13
    iglia
    -0.13
    esModule
    -0.13
    POSITIVE LOGITS
     Subject
    0.24
     unsubscribe
    0.21
    Subject
    0.21
    /msg
    0.21
     Digest
    0.20
    unsubscribe
    0.20
     Sent
    0.20
    ê´ijê³ł
    0.20
    Prev
    0.19
    bounce
    0.19
    Act Density 0.216%

    No Known Activations