INDEX
Explanations
The neuron activates on occurrences of the word “factory” (in code identifiers or comments).
New Auto-Interp
Negative Logits
統
-0.07
882
-0.06
input
-0.06
.compute
-0.06
_material
-0.06
exits
-0.06
McGregor
-0.06
input
-0.06
_annotation
-0.06
-fl
-0.06
POSITIVE LOGITS
Factory
0.06
READY
0.06
ทะ
0.06
factory
0.06
stile
0.06
가지고
0.06
kindness
0.06
ATIO
0.06
operative
0.06
JT
0.06
Activations Density 0.065%