INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     её
    -0.07
    ۱۹۷
    -0.07
     somehow
    -0.06
     competitiveness
    -0.06
     Elder
    -0.06
    	expected
    -0.06
    ?」↵↵
    -0.06
    conf
    -0.06
    embourg
    -0.06
    writes
    -0.06
    POSITIVE LOGITS
    0.07
    0.06
     رسانه
    0.06
    urgery
    0.06
     obsess
    0.06
     downloadable
    0.06
     Foley
    0.06
    -eng
    0.06
     gamer
    0.06
    .addRow
    0.06
    Act Density 0.018%

    No Known Activations