INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -0.09
     =
    -0.08
     messages
    -0.07
     Hook
    -0.07
    Hook
    -0.07
     hooks
    -0.07
     syn
    -0.07
     Sitemap
    -0.07
     служ
    -0.07
     forbind
    -0.07
    POSITIVE LOGITS
     dilution
    0.11
    (updated
    0.11
     weighting
    0.11
     diluted
    0.11
    weighted
    0.11
     averaging
    0.10
    Weighted
    0.10
     denominator
    0.10
     demographics
    0.10
     weighted
    0.10
    Act Density 0.039%

    No Known Activations