INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    Heating
    -0.08
    Of
    -0.08
    -0.07
    AVA
    -0.07
     heating
    -0.07
    He's
    -0.07
    ENG
    -0.07
     Heating
    -0.07
    Certainly
    -0.07
    [e
    -0.07
    POSITIVE LOGITS
    0.09
     بالح
    0.08
    명이
    0.08
     upro
    0.08
     अवस्थामा
    0.08
     beskr
    0.08
     appreciates
    0.08
     disebut
    0.08
     부산
    0.08
    0.08
    Act Density 0.010%

    No Known Activations