INDEX
Explanations
organizations
This neuron fires on ordinal “first” claims—i.e. mentions of something being the first entity to achieve or introduce something.
New Auto-Interp
Negative Logits
breathtaking
-0.07
CONTROL
-0.07
Chris
-0.06
Keller
-0.06
weet
-0.06
Abr
-0.06
Ot
-0.06
신청
-0.06
FIXME
-0.06
associated
-0.06
POSITIVE LOGITS
World
0.07
viewType
0.06
جد
0.06
jardin
0.06
ملي
0.06
ز
0.06
č
0.06
шту
0.06
ION
0.06
نمود
0.06
Activations Density 0.029%