INDEX
    Explanations

    the title or designation "Jr" indicating a junior or younger version of a person with the same name

    New Auto-Interp
    Negative Logits
     enc
    -0.71
     Winfrey
    -0.68
     utafitiHapana
    -0.65
    ilever
    -0.64
    APIView
    -0.64
     SAE
    -0.63
    HasAnnotation
    -0.63
     LPC
    -0.63
     HOF
    -0.63
     Mazda
    -0.62
    POSITIVE LOGITS
     Junior
    1.79
     junior
    1.73
    junior
    1.72
     JUNIOR
    1.70
    Junior
    1.68
     juniors
    1.51
     Jr
    1.49
     Juniors
    1.40
    Jr
    1.38
     Júnior
    1.34
    Act Density 0.076%

    No Known Activations