INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     آلة
    -0.09
     memorable
    -0.08
    KNOWN
    -0.08
     استاند
    -0.08
    oe
    -0.08
     сопр
    -0.08
     шулай
    -0.07
     над
    -0.07
     تعمیر
    -0.07
     horno
    -0.07
    POSITIVE LOGITS
     spinach
    0.12
    菠菜
    0.11
     菠菜
    0.08
     ACT
    0.08
     veggies
    0.08
    0.08
     Upt
    0.08
     obe
    0.08
     Erica
    0.08
     Veronica
    0.08
    Act Density 0.018%

    No Known Activations