INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -0.08
    Airport
    -0.08
     Airport
    -0.08
     прилож
    -0.08
     CDs
    -0.08
    Infl
    -0.08
    -0.08
     Inflation
    -0.07
    rocery
    -0.07
     Appliance
    -0.07
    POSITIVE LOGITS
     elaborate
    0.08
    èvre
    0.08
     elabor
    0.08
     nonstop
    0.08
    never
    0.07
    ean
    0.07
    Never
    0.07
    рист
    0.07
    0.07
     Never
    0.07
    Act Density 0.007%

    No Known Activations