INDEX
    Explanations

    URLs/domains

    New Auto-Interp
    Negative Logits
     bicarbon
    -0.09
    acrit
    -0.08
    λόγ
    -0.08
     wagers
    -0.08
     combats
    -0.08
    וקט
    -0.08
     pc
    -0.08
    лык
    -0.08
     cloves
    -0.08
     ricon
    -0.08
    POSITIVE LOGITS
     thinkers
    0.08
     conceptual
    0.07
     وت
    0.07
     thinker
    0.07
     siis
    0.07
     Denken
    0.07
     Vám
    0.07
     kase
    0.07
    inspect
    0.07
     impending
    0.07
    Act Density 0.006%

    No Known Activations