INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -0.09
     gland
    -0.08
    -0.08
     calculate
    -0.08
     stair
    -0.08
    -0.08
     anh
    -0.08
    	channel
    -0.07
    huizen
    -0.07
     gluc
    -0.07
    POSITIVE LOGITS
    Moon
    0.08
    -American
    0.08
     rom
    0.08
    -minded
    0.08
     crust
    0.08
     Bor
    0.08
    -owned
    0.07
     Civil
    0.07
     complaints
    0.07
    0.07
    Act Density 0.007%

    No Known Activations