INDEX
Explanations
This neuron activates on the phrase “current events.”
New Auto-Interp
Negative Logits
_el
-0.07
.Unsupported
-0.06
%i
-0.06
_OC
-0.06
_Selected
-0.06
ID
-0.06
_PI
-0.06
colabor
-0.06
das
-0.06
########################################
-0.06
POSITIVE LOGITS
nhiệm
0.07
textured
0.07
Exists
0.06
fixing
0.06
queues
0.06
andom
0.06
embodied
0.06
إ
0.06
нима
0.06
numeric
0.06
Activations Density 0.005%