INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Prec
    -0.08
     ged
    -0.08
     samenwerken
    -0.08
     Burst
    -0.08
     sprouts
    -0.07
    -0.07
    -0.07
    Prec
    -0.07
    MPP
    -0.07
     Maxim
    -0.07
    POSITIVE LOGITS
    0.08
    GO
    0.07
     Domen
    0.07
    (opts
    0.07
     GO
    0.07
    0.07
    alignment
    0.07
     brace
    0.07
     braces
    0.07
    Absent
    0.07
    Act Density 0.007%

    No Known Activations