INDEX
    Explanations

    proto-languages

    New Auto-Interp
    Negative Logits
     отсутствие
    -0.10
     figs
    -0.08
     rollout
    -0.08
    522
    -0.08
     наличие
    -0.08
     تفاصيل
    -0.07
     činjen
    -0.07
     disclaimer
    -0.07
     afinal
    -0.07
     nl
    -0.07
    POSITIVE LOGITS
    0.08
    ipot
    0.08
    -Semit
    0.08
     Indo
    0.08
    Saudi
    0.07
    uvian
    0.07
    0.07
     proto
    0.07
    erie
    0.07
    -Amer
    0.07
    Act Density 0.003%

    No Known Activations