INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Cic
    -0.08
     Crane
    -0.07
     clim
    -0.07
     mole
    -0.07
     Xi
    -0.07
     Julius
    -0.07
     Lind
    -0.07
     espí
    -0.07
    -0.07
     Wendy
    -0.07
    POSITIVE LOGITS
    Ago
    0.11
    0.10
     ago
    0.09
     جدًا
    0.09
    以来
    0.08
    0.08
    -lasting
    0.08
    所以
    0.08
     పాటు
    0.08
     عرص
    0.08
    Act Density 0.023%

    No Known Activations