INDEX
    Explanations

    references to martial arts and their instructors or achievements

    New Auto-Interp
    Negative Logits
    edis
    -0.16
    lok
    -0.15
     æľĿ
    -0.15
    jest
    -0.15
    onds
    -0.15
    лаж
    -0.14
    jes
    -0.14
    adel
    -0.14
     McGr
    -0.14
    ooth
    -0.13
    POSITIVE LOGITS
    _mD
    0.15
    uhn
    0.15
    egt
    0.15
    ÙĦÙĬÙģ
    0.14
    _mC
    0.14
    ô
    0.14
    ecast
    0.13
     Param
    0.13
    ateurs
    0.13
    _tD
    0.13
    Act Density 0.096%

    No Known Activations