INDEX
    Explanations

    coordinates and ratios

    New Auto-Interp
    Negative Logits
     Herc
    -0.08
     presenting
    -0.08
     presents
    -0.08
     presentan
    -0.07
    ודות
    -0.07
     abol
    -0.07
    erns
    -0.07
     hano
    -0.07
     presentada
    -0.07
     auparavant
    -0.07
    POSITIVE LOGITS
     interpol
    0.11
     averaged
    0.11
     blended
    0.11
    Interpol
    0.10
     Aver
    0.10
     interpolate
    0.10
     blending
    0.09
     averaging
    0.09
     Blend
    0.09
     interpolation
    0.09
    Act Density 0.023%

    No Known Activations