INDEX
Negative Logits
proactive
-0.08
proactively
-0.08
yny
-0.07
orton
-0.07
pener
-0.07
gens
-0.07
illustr
-0.07
Specified
-0.07
īn
-0.07
IID
-0.07
POSITIVE LOGITS
weakened
0.11
corrupted
0.11
fragmented
0.11
impaired
0.10
amidst
0.10
muff
0.10
whispered
0.10
呻
0.10
gar
0.10
malformed
0.09
Activations Density 0.010%