INDEX
Explanations
years of age
mentions of age-related terms or descriptors
New Auto-Interp
Negative Logits
achus
-0.92
Clever
-0.69
alus
-0.68
anus
-0.66
subp
-0.65
enthusi
-0.65
anooga
-0.64
earch
-0.63
aco
-0.62
otos
-0.60
POSITIVE LOGITS
ago
0.80
anniversary
0.78
iversary
0.77
long
0.75
grain
0.74
Anniversary
0.74
ably
0.72
commem
0.69
ados
0.69
rule
0.69
Activations Density 0.037%