INDEX
Explanations
Wikipedia articles
This neuron does not activate for any tokens in the samples—it appears to be effectively inactive.
New Auto-Interp
Negative Logits
hlad
-0.07
.gsub
-0.07
кількості
-0.07
VOL
-0.06
(_)
-0.06
Par
-0.06
ุธ
-0.06
URES
-0.06
_subtitle
-0.06
interp
-0.06
POSITIVE LOGITS
-book
0.07
irk
0.06
meantime
0.06
plants
0.06
eler
0.06
,n
0.06
intuit
0.06
ункци
0.06
NTN
0.06
anne
0.06
Activations Density 0.002%