INDEX
Explanations
signs or posting notices
The neuron activates on words and phrases describing physically putting up or displaying items (e.g. posting, putting up, or lighting up signs/posters).
New Auto-Interp
Negative Logits
zásad
-0.07
hton
-0.06
inv
-0.06
їм
-0.06
recommending
-0.06
Interview
-0.06
Nga
-0.06
yy
-0.06
school
-0.06
bag
-0.06
POSITIVE LOGITS
çözüm
0.07
ілі
0.06
realloc
0.06
Díky
0.06
almonds
0.06
.volume
0.06
Signal
0.06
{!!0.06
ToolBar
0.06
avra
0.06
Activations Density 0.037%