INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -0.10
     fuertes
    -0.09
    skraft
    -0.09
    ğu
    -0.08
    said
    -0.08
    -0.08
     starke
    -0.08
    reme
    -0.08
     güçlü
    -0.08
     sterk
    -0.08
    POSITIVE LOGITS
     hel
    0.09
     demonstra
    0.08
     universit
    0.08
     dilem
    0.08
     prison
    0.07
     seminar
    0.07
    0.07
    GM
    0.07
     Fo
    0.07
     Golden
    0.07
    Act Density 0.003%

    No Known Activations