INDEX
Explanations
age indications expressed in a "number-year-old" format
numerical references to the ages of children
New Auto-Interp
Negative Logits
flush
-0.65
akin
-0.64
Dialogue
-0.64
ufficient
-0.62
urgy
-0.61
ausible
-0.60
torches
-0.60
lobb
-0.59
aturday
-0.59
achus
-0.59
POSITIVE LOGITS
olds
1.15
ago
0.88
old
0.80
OLD
0.78
old
0.76
anniversary
0.74
olds
0.72
iversary
0.71
veteran
0.67
pregnant
0.66
Activations Density 0.047%