INDEX
Explanations
The neuron detects mentions of caring about or worrying over what other people think.
New Auto-Interp
Negative Logits
liebe
-0.06
reefs
-0.06
нили
-0.06
Stam
-0.06
'na
-0.06
ams
-0.06
(Guid
-0.06
italize
-0.06
ček
-0.06
zvlá
-0.06
POSITIVE LOGITS
درجة
0.06
tc
0.06
-de
0.06
защ
0.06
donation
0.06
_);↵
0.06
اق
0.06
dhcp
0.06
设置
0.06
Android
0.06
Activations Density 0.022%