INDEX
    Explanations

    prepositions

    New Auto-Interp
    Negative Logits
     Basketball
    -0.07
    uman
    -0.06
     &
    -0.06
    /screens
    -0.06
    omore
    -0.06
    									
    -0.06
    <Route
    -0.06
     Fishing
    -0.06
    quez
    -0.06
     personal
    -0.06
    POSITIVE LOGITS
    كييف
    0.07
    _ADV
    0.07
    _abort
    0.06
    Prince
    0.06
     پی
    0.06
    0.06
     ;↵
    0.06
     ẩn
    0.06
    LL
    0.06
    örper
    0.06
    Act Density 0.103%

    No Known Activations