INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    альными
    -0.07
     pools
    -0.07
    stylesheet
    -0.07
     laz
    -0.07
    SOLE
    -0.06
    ODB
    -0.06
    ovaného
    -0.06
     unions
    -0.06
    Containers
    -0.06
     Compression
    -0.06
    POSITIVE LOGITS
     Senator
    0.07
     senator
    0.07
     sexism
    0.06
     spiel
    0.06
    (bot
    0.06
     Congressional
    0.06
     xhttp
    0.06
     گل
    0.06
     senators
    0.06
     sections
    0.06
    Act Density 0.028%

    No Known Activations