INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    isations
    -0.09
     salesman
    -0.08
    ishi
    -0.08
    vou
    -0.08
     woes
    -0.08
    yan
    -0.08
    -ish
    -0.08
     Constraint
    -0.08
    78
    -0.08
    -0.08
    POSITIVE LOGITS
     кроме
    0.09
     behalve
    0.09
     excepto
    0.08
     minors
    0.08
    ,包括
    0.07
     majority
    0.07
     adjud
    0.07
     pog
    0.07
     indication
    0.07
     sexual
    0.07
    Act Density 0.009%

    No Known Activations