INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     lust
    -0.08
     uranium
    -0.07
    gal
    -0.07
     jir
    -0.07
     rf
    -0.07
     Mn
    -0.07
    itch
    -0.07
    -0.07
     quint
    -0.07
     			
    -0.07
    POSITIVE LOGITS
    0.08
    onc
    0.08
     scored
    0.07
    0.07
     devastating
    0.07
    образ
    0.07
     conceded
    0.07
    odd
    0.07
    Ontology
    0.07
     остав
    0.07
    Act Density 0.006%

    No Known Activations