INDEX
Explanations
diseases
This neuron detects mentions of medical or biomedical topics, especially disease names, treatments, infections, and related terminology.
New Auto-Interp
Negative Logits
Sociology
-0.07
enaries
-0.06
samp
-0.06
filmmaker
-0.06
一页
-0.06
iative
-0.06
Essex
-0.06
ceased
-0.06
TECT
-0.06
页
-0.06
POSITIVE LOGITS
�
0.06
Выб
0.06
amused
0.06
==↵
0.06
ιθ
0.06
typ
0.06
swinging
0.06
());↵
0.06
Datensch
0.06
unconstitutional
0.06
Activations Density 0.023%