INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    				    
    -0.08
    'était
    -0.07
     apart
    -0.07
    sto
    -0.07
    ibo
    -0.07
    _order
    -0.06
    374
    -0.06
     Jeb
    -0.06
     BAS
    -0.06
     fır
    -0.06
    POSITIVE LOGITS
     CNN
    0.09
    CNN
    0.08
    NN
    0.07
    nn
    0.07
    helper
    0.06
     dawn
    0.06
    ظم
    0.06
    0.06
    alertView
    0.06
    .pin
    0.06
    Act Density 0.004%

    No Known Activations