INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     animales
    -0.11
     animais
    -0.10
     gatos
    -0.08
     animals
    -0.08
    قيب
    -0.08
     acost
    -0.08
    -0.08
     animaux
    -0.08
     objetivos
    -0.07
     ಲಕ್ಷ
    -0.07
    POSITIVE LOGITS
     burning
    0.09
     ASTM
    0.08
     burn
    0.08
     merging
    0.07
     Burning
    0.07
    0.07
     incest
    0.07
    ేందుకు
    0.07
    Đ
    0.07
     disent
    0.07
    Act Density 0.002%

    No Known Activations