INDEX
Explanations
phrases related to periods or moments in time
phrases indicating periods of significant social or emotional change
New Auto-Interp
Negative Logits
azines
-0.91
handle
-0.85
ittens
-0.78
iaries
-0.69
ME
-0.65
era
-0.65
pire
-0.65
eds
-0.64
thing
-0.64
bones
-0.63
POSITIVE LOGITS
sorts
1.22
heightened
0.98
unparalleled
0.96
refinement
0.95
desperation
0.94
contrasts
0.92
intimidation
0.92
intense
0.90
consolidation
0.90
continual
0.89
Activations Density 0.182%