INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -0.08
     ontdek
    -0.07
    ise
    -0.07
     Kang
    -0.07
     ontdekken
    -0.07
     Beach
    -0.07
     ontde
    -0.07
    rror
    -0.07
     BR
    -0.07
     coconut
    -0.06
    POSITIVE LOGITS
     forvent
    0.10
     überhaupt
    0.09
     এত
    0.09
     Quite
    0.09
     respectable
    0.09
     supposedly
    0.08
     Considering
    0.08
     eigentlich
    0.08
     ضروری
    0.08
    Expected
    0.08
    Act Density 0.053%

    No Known Activations