INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    PopupMenu
    -0.07
     unfortunately
    -0.07
     Erik
    -0.06
     unfortunate
    -0.06
     paciente
    -0.06
    290
    -0.06
    647
    -0.06
     furthermore
    -0.06
     mam
    -0.06
    count
    -0.06
    POSITIVE LOGITS
    .Style
    0.07
     karış
    0.06
     کی
    0.06
    %^
    0.06
    (bg
    0.06
    Record
    0.06
     şah
    0.06
     colle
    0.06
    .escape
    0.06
    ương
    0.06
    Act Density 0.066%

    No Known Activations