INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    Abs
    -0.08
    Conf
    -0.08
    -0.07
    Poss
    -0.07
    Chap
    -0.07
    Will
    -0.07
     પુર
    -0.07
    Decor
    -0.07
     väär
    -0.07
    Array
    -0.07
    POSITIVE LOGITS
     concepts
    0.10
    0.09
     Concept
    0.09
     conceptos
    0.08
     concepto
    0.08
     Concepts
    0.08
     концеп
    0.08
    osest
    0.08
     Kalou
    0.08
     koncept
    0.08
    Act Density 0.007%

    No Known Activations