INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    common
    -0.07
    acc
    -0.06
     anomalies
    -0.06
    .acc
    -0.06
     Women
    -0.06
    	text
    -0.06
    -0.06
    の中
    -0.06
    (position
    -0.06
     neuroscience
    -0.06
    POSITIVE LOGITS
     Ebola
    0.17
     haf
    0.08
     строки
    0.07
     популяр
    0.06
     bri
    0.06
     adel
    0.06
     Bever
    0.06
     EDIT
    0.06
     ücretsiz
    0.06
    ывал
    0.06
    Act Density 0.001%

    No Known Activations