INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    &apos
    -0.06
     ------------------------------------------------------------------------------------------------
    -0.06
     bik
    -0.06
     Higgins
    -0.06
                                                      
    -0.06
     --------------------
    -0.06
     ----------------------------------------------------------------------------------------------------------------
    -0.06
     manera
    -0.06
     gel
    -0.06
    .SIZE
    -0.06
    POSITIVE LOGITS
    covering
    0.08
    (eq
    0.07
    ("("
    0.07
    عی
    0.06
    plemented
    0.06
    ecd
    0.06
    скую
    0.06
     Parliament
    0.06
     semantic
    0.06
     behaviors
    0.06
    Act Density 0.067%

    No Known Activations