INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    is
    1.18
    να
    0.98
    ни
    0.97
    of
    0.95
    os
    0.90
    ра
    0.89
    ți
    0.88
    ्य
    0.82
    க்கு
    0.81
    0.80
    POSITIVE LOGITS
    _
    1.38
     traum
    1.10
     trauma
    1.08
     Trauma
    0.96
            
    0.94
    {
    0.93
                   
    0.91
    ارك
    0.91
     traumat
    0.90
     
    0.89
    Act Density 0.010%

    No Known Activations