INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     to
    1.43
     as
    1.41
    را
    1.31
    غ
    1.30
     are
    1.28
     و
    1.25
     and
    1.24
    ва
    1.20
    ö
    1.15
    ü
    1.13
    POSITIVE LOGITS
    1.33
     Figura
    1.21
     startDate
    1.15
    '))
    1.13
     Figuren
    1.12
                    
    1.08
    Figura
    1.06
    Ма
    1.05
    1.04
     AudioClip
    1.02
    Act Density 0.012%

    No Known Activations