INDEX
Explanations
information related to the ages and years of individuals
numerical age references
New Auto-Interp
Negative Logits
teen
-0.72
teens
-0.71
teenager
-0.69
teenagers
-0.68
teenage
-0.66
Teens
-0.59
Teen
-0.58
adolescent
-0.58
Teen
-0.58
adolescente
-0.56
POSITIVE LOGITS
ſſung
0.62
<unused52>
0.60
arşivlendi
0.60
<unused8>
0.60
<unused28>
0.60
<unused32>
0.59
<unused51>
0.59
<unused23>
0.59
[@BOS@]
0.59
<unused3>
0.59
Activations Density 0.039%