INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Pest
    -0.08
     rat
    -0.07
     pest
    -0.07
     colleges
    -0.07
    Ho
    -0.07
    Gray
    -0.07
     mouse
    -0.07
    /in
    -0.07
    rift
    -0.07
    مة
    -0.07
    POSITIVE LOGITS
     mango
    0.10
    Functor
    0.08
     пок
    0.08
     restoration
    0.08
     Restoration
    0.08
     wildly
    0.08
     tropical
    0.08
    _SHARE
    0.07
     cuts
    0.07
     orally
    0.07
    Act Density 0.003%

    No Known Activations