INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Uran
    -0.09
     genie
    -0.08
    iphone
    -0.08
    (U
    -0.08
    chmod
    -0.08
     divorced
    -0.08
     proph
    -0.08
     urinary
    -0.07
     inc
    -0.07
     imag
    -0.07
    POSITIVE LOGITS
     anchored
    0.09
     Barnes
    0.08
     течение
    0.08
     Benton
    0.08
     multic
    0.08
    Anch
    0.08
     Children
    0.08
     Anch
    0.08
    0.08
     Bill
    0.07
    Act Density 0.002%

    No Known Activations