INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Boilers
    -0.09
    	level
    -0.09
     тух
    -0.08
     бетон
    -0.08
     Messer
    -0.08
     inmueble
    -0.08
     Producers
    -0.08
     Intelli
    -0.08
    اعة
    -0.07
    -0.07
    POSITIVE LOGITS
    0.08
    ellite
    0.08
    Archived
    0.08
    Scaling
    0.07
     pend
    0.07
     raisins
    0.07
    sit
    0.07
     pendant
    0.07
    .archive
    0.07
    _scal
    0.07
    Act Density 0.004%

    No Known Activations