INDEX
Explanations
The neuron fires on standalone numeric tokens (especially those in the teens to low double digits) used as volume, issue, or page numbers in journal citation metadata.
New Auto-Interp
Negative Logits
quoted
-0.06
металли
-0.06
termination
-0.06
division
-0.06
／
-0.06
_reader
-0.06
Php
-0.06
Razor
-0.06
والإ
-0.05
odies
-0.05
POSITIVE LOGITS
力量
0.07
=:
0.06
ریم
0.06
ψε
0.06
/icon
0.06
nesta
0.06
رق
0.06
ocate
0.06
-pt
0.06
θλη
0.06
Activations Density 0.002%