INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     ambul
    -0.08
     camin
    -0.08
     przede
    -0.08
     seated
    -0.08
    constit
    -0.07
     pestic
    -0.07
    .Notify
    -0.07
     atualizar
    -0.07
     actualizar
    -0.07
    stre
    -0.07
    POSITIVE LOGITS
     backstage
    0.08
     anime
    0.08
     Airlines
    0.08
    Anim
    0.08
     Netflix
    0.07
     cosplay
    0.07
     Eurovision
    0.07
    手游
    0.07
     soff
    0.07
    Anime
    0.07
    Act Density 0.003%

    No Known Activations