INDEX
    Explanations

    punctuation marks, particularly periods and commas

    New Auto-Interp
    Negative Logits
    ivr
    -0.16
    INY
    -0.15
    embro
    -0.15
    azzi
    -0.14
    iny
    -0.14
     yet
    -0.14
    ings
    -0.14
    issent
    -0.14
    orer
    -0.14
    šem
    -0.14
    POSITIVE LOGITS
     Cox
    0.15
    hausen
    0.14
    forth
    0.14
    em
    0.14
     ones
    0.14
    addError
    0.13
    ocker
    0.13
    _DST
    0.13
     ngoÃłi
    0.13
     nameLabel
    0.13
    Act Density 0.025%

    No Known Activations