INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    नों
    -0.09
    ned
    -0.08
    icron
    -0.08
    ensional
    -0.08
    ियन
    -0.08
    rikstad
    -0.08
    ration
    -0.08
    utation
    -0.08
     plaas
    -0.08
    inho
    -0.08
    POSITIVE LOGITS
     laiss
    0.12
     lasci
    0.12
    Leave
    0.11
     Leave
    0.11
     laissé
    0.11
     leave
    0.11
     quitté
    0.10
     leaving
    0.10
    _leave
    0.10
    leave
    0.10
    Act Density 0.061%

    No Known Activations