INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    0.39
     administratif
    0.35
    0.34
    0.34
    0.34
     şeyler
    0.33
     perusahaan
    0.33
     özellikle
    0.33
    0.33
    0.32
    POSITIVE LOGITS
    +
    0.60
     +
    0.47
    +\
    0.46
    4
    0.44
    +(
    0.44
    f
    0.43
    6
    0.43
    x
    0.42
            
    0.42
        
    0.41
    Act Density 0.294%

    No Known Activations