INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     undoubtedly
    1.21
     Конечно
    1.17
    ри
    1.11
     unquestionably
    1.03
     tentunya
    1.02
     eventuali
    1.02
     Essentially
    1.01
     certainly
    0.99
     básicamente
    0.99
    Fantastic
    0.99
    POSITIVE LOGITS
    (?)
    1.23
     (?)
    1.17
     niet
    1.10
     nicht
    1.07
     didn
    1.04
     Poco
    1.04
     not
    1.03
     agak
    1.02
     وليس
    0.98
    nicht
    0.97
    Act Density 0.036%

    No Known Activations