INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    تمر
    -0.08
    So
    -0.08
    -0.07
    иден
    -0.07
    үүл
    -0.07
    Н
    -0.07
    Happy
    -0.07
    Euro
    -0.07
     reflects
    -0.07
    (em
    -0.07
    POSITIVE LOGITS
     Pear
    0.08
     Prote
    0.07
    bell
    0.07
     дон
    0.07
     rinn
    0.07
     cork
    0.07
     chanson
    0.07
     대신
    0.07
     Depot
    0.07
     Celt
    0.07
    Act Density 0.031%

    No Known Activations