INDEX
Explanations
age restrictions
This neuron activates on statements specifying age requirements (e.g., minimum ages like “18 years old” or “21 years old”).
New Auto-Interp
Negative Logits
_corpus
-0.08
woodland
-0.06
agua
-0.06
Vanity
-0.06
mdp
-0.06
讀
-0.06
Venue
-0.06
murdering
-0.06
альные
-0.05
liers
-0.05
POSITIVE LOGITS
.SuppressLint
0.07
argin
0.07
enhance
0.07
newInstance
0.06
✓
0.06
yı
0.06
refugee
0.06
fold
0.06
нить
0.06
conseg
0.06
Activations Density 0.008%