INDEX
Explanations
software
The neuron fires on mentions of statistical‐analysis software names (often with version numbers).
New Auto-Interp
Negative Logits
bak
-0.07
Glasses
-0.07
элем
-0.06
Material
-0.06
elled
-0.06
deco
-0.06
Her
-0.06
erald
-0.06
жень
-0.06
Legal
-0.06
POSITIVE LOGITS
0.07
을
0.07
بـ
0.06
드립니다
0.06
ประม
0.06
(xhr
0.06
CST
0.06
family
0.06
xD
0.06
filtro
0.06
Activations Density 0.008%