INDEX
Explanations
The neuron flags section headings that begin with “About.”
New Auto-Interp
Negative Logits
Colony
-0.07
CppMethodInitialized
-0.07
colonies
-0.07
ίν
-0.07
(strip
-0.07
iała
-0.06
(dom
-0.06
код
-0.06
incons
-0.06
πά
-0.06
POSITIVE LOGITS
About
0.10
About
0.08
about
0.08
ABOUT
0.07
about
0.06
дотрим
0.06
ware
0.06
TILE
0.06
introduce
0.06
634
0.06
Activations Density 0.001%