INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    disease
    -1.03
    OGND
    -0.98
    Disease
    -0.96
     disease
    -0.94
     DISEASE
    -0.94
     propOrder
    -0.90
     Roskov
    -0.90
    RegressionTest
    -0.89
     Disease
    -0.88
     ziekte
    -0.85
    POSITIVE LOGITS
     is
    0.59
     induction
    0.56
     .
    0.53
    toBeTruthy
    0.53
    ResumeLayout
    0.51
    ;
    0.51
     with
    0.51
     alpha
    0.51
     by
    0.50
     Alpha
    0.49
    Act Density 1.609%

    No Known Activations