INDEX
    Explanations

    phrases or sentences containing quotation marks

    punctuation, particularly quotation marks and exclamation points

    New Auto-Interp
    Negative Logits
    nex
    -0.76
    ħ
    -0.73
     enriched
    -0.68
    ent
    -0.68
    uster
    -0.67
    ware
    -0.67
    Į
    -0.66
    ª
    -0.66
    croft
    -0.63
    ı
    -0.63
    POSITIVE LOGITS
    ONSORED
    0.93
    !'"
    0.93
    acebook
    0.91
    ?'"
    0.91
    ,'"
    0.90
    ',"
    0.86
    "[
    0.83
    terday
    0.82
    xual
    0.82
     Tanz
    0.82
    Act Density 0.009%

    No Known Activations