INDEX
Explanations
ages or mentions of people's ages, specifically those ending in '0 and '9
references to people's ages
New Auto-Interp
Negative Logits
icter
-0.95
ettings
-0.85
mathemat
-0.85
earch
-0.80
pecially
-0.80
inventoryQuantity
-0.80
okin
-0.79
ËĪ
-0.79
irtual
-0.79
atch
-0.78
POSITIVE LOGITS
Frenchman
0.75
Bernard
0.71
refrain
0.71
woman
0.69
man
0.68
York
0.67
Anton
0.66
Sa
0.65
TD
0.65
Slov
0.64
Activations Density 0.023%