INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ikaanse
    -0.10
    -0.10
    leneck
    -0.09
    čnega
    -0.09
     په
    -0.09
    енә
    -0.09
    üne
    -0.09
    čina
    -0.08
     Effective
    -0.08
    íbrio
    -0.08
    POSITIVE LOGITS
    _all
    0.18
    	all
    0.17
    (all
    0.17
    .all
    0.17
    @All
    0.16
     allat
    0.16
    'all
    0.16
     all
    0.16
    ’all
    0.16
    -all
    0.16
    Act Density 0.028%

    No Known Activations