INDEX
    Explanations

    foreign language prefixes and words

    New Auto-Interp
    Negative Logits
     non
    0.44
     *
    0.38
     can
    0.37
     fles
    0.34
     extra
    0.34
    0.33
     matte
    0.33
     new
    0.33
     could
    0.33
    eer
    0.32
    POSITIVE LOGITS
    resión
    0.69
    ábbi
    0.65
    respuesta
    0.60
    resultados
    0.60
    0.59
    álen
    0.59
    posición
    0.59
    пределение
    0.58
    ozione
    0.58
    dimensioni
    0.58
    Act Density 0.255%

    No Known Activations