INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Unterschiede
    -0.08
     diferencia
    -0.08
    /results
    -0.08
     diferencias
    -0.08
     besondere
    -0.07
    (Time
    -0.07
    (Group
    -0.07
     diferença
    -0.07
     voulu
    -0.07
     Austin
    -0.07
    POSITIVE LOGITS
     Ling
    0.09
     ling
    0.08
     blink
    0.08
     syll
    0.08
     blur
    0.08
     kb
    0.08
     кли
    0.08
     wl
    0.08
     KL
    0.08
     khẩu
    0.08
    Act Density 0.004%

    No Known Activations