INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    кра
    -0.10
    -0.09
    lyde
    -0.09
    لاک
    -0.09
     şa
    -0.08
    faranga
    -0.08
     гуз
    -0.08
    стэр
    -0.08
     silky
    -0.08
    сьць
    -0.08
    POSITIVE LOGITS
    omial
    0.38
    om
    0.36
    oms
    0.24
    omone
    0.23
    OM
    0.23
    ominator
    0.21
    ോമ
    0.21
    omorphic
    0.20
    ોમ
    0.19
    omia
    0.19
    Act Density 0.009%

    No Known Activations