INDEX
Explanations
ages related to specific ages
mentions of age descriptions related to individuals
New Auto-Interp
Negative Logits
Scrib
-0.73
THR
-0.66
proced
-0.65
hots
-0.62
Tac
-0.61
redund
-0.61
elimination
-0.60
exits
-0.58
vibrations
-0.56
perme
-0.55
POSITIVE LOGITS
old
1.41
olds
1.30
OLD
1.01
appointed
0.98
young
0.96
long
0.95
prison
0.90
daughter
0.89
older
0.88
woman
0.85
Activations Density 0.037%