INDEX
    Explanations

    references to notable inventions and their inventors, particularly in aviation and mechanical devices

    New Auto-Interp
    Negative Logits
    setTarget
    -0.67
    nappropriate
    -0.62
    unnitel
    -0.61
     McKnight
    -0.60
    indak
    -0.59
     ekos
    -0.59
    -0.58
    \}_{
    -0.57
     menge
    -0.57
    strij
    -0.57
    POSITIVE LOGITS
    expandindo
    0.90
     WWI
    0.67
    twimg
    0.67
    Orsay
    0.63
    ppelin
    0.62
     &___
    0.62
     Maud
    0.60
     suffrage
    0.60
     dago
    0.60
     bbb
    0.59
    Act Density 0.568%

    No Known Activations