INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Herz
    -0.07
     jihadist
    -0.07
    uploads
    -0.06
     ":"
    -0.06
    kehr
    -0.06
     pasture
    -0.06
     perish
    -0.06
    .LOG
    -0.06
    ena
    -0.06
    .sig
    -0.06
    POSITIVE LOGITS
     finer
    0.06
    .at
    0.06
     Money
    0.06
     getSize
    0.06
     financially
    0.06
     girlfriends
    0.06
     Québec
    0.06
    prising
    0.06
     політи
    0.06
     We
    0.06
    Act Density 0.019%

    No Known Activations