INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    176
    -0.07
    LX
    -0.07
    -wise
    -0.07
    Ix
    -0.07
     nul
    -0.07
     Rah
    -0.07
    uptools
    -0.07
    -0.07
    صل
    -0.07
    _META
    -0.07
    POSITIVE LOGITS
     doorstep
    0.10
     кабин
    0.10
     hometown
    0.09
     mailbox
    0.09
     доме
    0.09
     inbox
    0.09
     driveway
    0.09
     workspace
    0.09
     sehari
    0.08
     кабинет
    0.08
    Act Density 0.077%

    No Known Activations