INDEX
Explanations
The neuron fires on mentions of train stations or other major transit hubs.
New Auto-Interp
Negative Logits
=options
-0.07
Program
-0.07
_maker
-0.07
Locator
-0.06
Volume
-0.06
Jewish
-0.06
approach
-0.06
SHR
-0.06
Syrian
-0.06
Penguin
-0.06
POSITIVE LOGITS
breakout
0.06
inet
0.06
↵↵
0.06
_EM
0.06
��态
0.06
',{↵0.06
ssid
0.06
운드
0.06
́t
0.06
prům
0.06
Activations Density 0.015%