INDEX
Explanations
volunteer
This neuron responds to mentions of volunteering or stepping up to take part in the act (e.g. “volunteer,” “volunteered,” “act”).
New Auto-Interp
Negative Logits
standings
-0.08
陵
-0.07
bố
-0.06
Reform
-0.06
Highway
-0.06
amaged
-0.06
Prix
-0.06
iče
-0.06
_slug
-0.06
Pey
-0.06
POSITIVE LOGITS
alerts
0.07
|;↵
0.07
００
0.07
;
0.06
163
0.06
yourself
0.06
traditionally
0.06
yourselves
0.06
doubles
0.06
libraries
0.06
Activations Density 0.006%