INDEX
    Explanations

    terms related to the concept of "double" or "duality."

    New Auto-Interp
    Negative Logits
    viewBox
    -0.41
    versammlung
    -0.39
    zeitung
    -0.39
    prefixer
    -0.39
     ultimi
    -0.38
     personeel
    -0.37
    UNRELATED
    -0.36
    BagConstraints
    -0.36
    baarheid
    -0.36
     přij
    -0.36
    POSITIVE LOGITS
     double
    0.79
     dual
    0.78
     DOUBLE
    0.72
     Double
    0.69
     doble
    0.67
     twin
    0.64
    double
    0.63
    transQ
    0.62
     двой
    0.62
     Dual
    0.61
    Act Density 0.059%

    No Known Activations