INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     drone
    -0.08
     تخ
    -0.08
     civilians
    -0.08
     війсь
    -0.08
    -0.07
     bush
    -0.07
     việc
    -0.07
     quân
    -0.07
    Military
    -0.07
     अक्ष
    -0.07
    POSITIVE LOGITS
     Booth
    0.09
     Chem
    0.09
    /mol
    0.08
     Macintosh
    0.08
    .PUBLIC
    0.08
    ifstream
    0.08
     mmol
    0.08
    'autre
    0.08
     aliqu
    0.08
    benz
    0.08
    Act Density 0.002%

    No Known Activations