INDEX
    Explanations

    punctuation marks and question marks

    New Auto-Interp
    Negative Logits
    inker
    -0.15
    adel
    -0.14
    iasi
    -0.13
    eniable
    -0.13
    ény
    -0.13
    оÑĢи
    -0.13
     GRAT
    -0.13
     Stars
    -0.13
    LoggedIn
    -0.13
    iform
    -0.13
    POSITIVE LOGITS
    by
    0.24
    Posted
    0.23
     Posted
    0.21
     posted
    0.18
    ================
    0.17
    posted
    0.16
    admin
    0.15
    egt
    0.15
    Uploader
    0.15
    ulace
    0.15
    Act Density 0.307%

    No Known Activations