INDEX
Explanations
prepositional phrases indicating status or comparison
New Auto-Interp
Negative Logits
Bots
-0.61
deen
-0.61
lean
-0.61
idity
-0.60
eton
-0.60
cia
-0.57
enery
-0.57
airs
-0.56
rises
-0.56
coefficients
-0.55
POSITIVE LOGITS
understatement
0.82
integral
0.78
anomaly
0.77
staple
0.76
starter
0.73
rarity
0.73
PIT
0.70
consolation
0.70
venient
0.70
manifestation
0.68
Activations Density 0.917%