INDEX
Explanations
The neuron fires on words describing hiking activities and trail details.
New Auto-Interp
Negative Logits
nid
-0.06
Nguyễn
-0.06
myst
-0.06
magic
-0.06
Nina
-0.06
ैय
-0.06
Tickets
-0.06
Triumph
-0.06
вза
-0.06
Dto
-0.06
POSITIVE LOGITS
0.07
کتاب
0.07
ensation
0.07
/gr
0.06
scientist
0.06
лон
0.06
/single
0.06
tabs
0.06
に出
0.06
společ
0.06
Activations Density 0.025%