INDEX
    Explanations

    mentions of martial arts and related credentials

    New Auto-Interp
    Negative Logits
    izz
    -0.16
     Fowler
    -0.15
    é»
    -0.15
     kraje
    -0.15
    ãģĵãģ¡ãĤī
    -0.15
    ण
    -0.14
    ügen
    -0.14
    NCY
    -0.14
     ÙĤÙĬ
    -0.14
    izza
    -0.14
    POSITIVE LOGITS
     Erotik
    0.16
     Prompt
    0.15
     nit
    0.15
     Nit
    0.15
    prompt
    0.14
    ordum
    0.14
     compress
    0.14
     UIL
    0.14
    naments
    0.13
     submodule
    0.13
    Act Density 0.027%

    No Known Activations