INDEX
    Explanations

    punctuation marks and structural elements in text

    New Auto-Interp
    Negative Logits
     Singleton
    -0.14
    xbd
    -0.14
    /vnd
    -0.13
    ácil
    -0.13
    bourg
    -0.13
    èĬ
    -0.12
     conf
    -0.12
     Alley
    -0.12
    ksen
    -0.12
     newer
    -0.12
    POSITIVE LOGITS
    urve
    0.19
    untime
    0.16
    nown
    0.15
    ayload
    0.15
    õi
    0.14
    abal
    0.14
     enumerator
    0.13
    ơi
    0.13
    imes
    0.13
    Corner
    0.13
    Act Density 0.264%

    No Known Activations