INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -0.09
    _construct
    -0.08
    ("#{
    -0.08
    -0.07
     eksempel
    -0.07
    -0.07
    -Me
    -0.07
    ähler
    -0.07
     dúvida
    -0.07
    								  
    -0.07
    POSITIVE LOGITS
     kakhulu
    0.11
     (>
    0.10
     enough
    0.09
     جدًا
    0.09
     جداً
    0.09
     innen
    0.09
    तम
    0.09
    Enough
    0.08
    તમ
    0.08
     ترین
    0.08
    Act Density 0.005%

    No Known Activations