INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    _git
    -0.07
    Characteristic
    -0.07
     coord
    -0.07
     injections
    -0.07
    Las
    -0.07
    _current
    -0.06
     fatalities
    -0.06
     weighs
    -0.06
    306
    -0.06
    Todos
    -0.06
    POSITIVE LOGITS
     fuzzy
    0.08
    _TypeDef
    0.07
     bozuk
    0.07
     resultSet
    0.06
     ffm
    0.06
    uzzy
    0.06
     fuzz
    0.06
     Joey
    0.06
     cunt
    0.06
     деле
    0.06
    Act Density 0.002%

    No Known Activations