INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    [int
    -0.07
     supermarkets
    -0.06
     Müdür
    -0.06
     supermarket
    -0.06
    (!$
    -0.06
    _request
    -0.06
     plight
    -0.06
    Store
    -0.06
     отмет
    -0.06
    -0.06
    POSITIVE LOGITS
     passion
    0.17
     Passion
    0.14
     passions
    0.10
     passionately
    0.10
     passionate
    0.09
     Bannon
    0.08
     pic
    0.07
    ion
    0.07
     packed
    0.07
     esas
    0.07
    Act Density 0.006%

    No Known Activations