INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    of
    -0.08
    rcode
    -0.08
    ovy
    -0.08
    amh
    -0.08
    431
    -0.08
    bd
    -0.07
    ocoa
    -0.07
     hsv
    -0.07
    Gen
    -0.07
    hle
    -0.07
    POSITIVE LOGITS
     Ches
    0.08
     Chill
    0.08
     Weis
    0.08
     Fernando
    0.08
     sufrido
    0.08
     Heart
    0.08
     дых
    0.08
     Presiden
    0.08
    0.08
     защищ
    0.08
    Act Density 0.003%

    No Known Activations