INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     year
    0.60
    0.56
    aid
    0.54
    <start_of_image>
    0.51
    year
    0.50
     calendar
    0.50
     omn
    0.49
     riz
    0.49
     calendário
    0.47
    anza
    0.47
    POSITIVE LOGITS
     不过
    0.52
     因为
    0.50
     कुनै
    0.49
    0.48
     الوحد
    0.48
     đám
    0.47
    0.46
     Comerc
    0.46
    blusas
    0.46
     Verification
    0.46
    Act Density 0.004%

    No Known Activations