INDEX
Explanations
The neuron fires on mentions of medical treatments or interventions (e.g. physical therapy, medications, surgery).
New Auto-Interp
Negative Logits
bitte
-0.06
매우
-0.06
باز
-0.06
وینت
-0.06
Triangle
-0.06
Tos
-0.06
벽
-0.06
細
-0.06
ум
-0.06
ρό
-0.06
POSITIVE LOGITS
_SCORE
0.06
.yellow
0.06
disclose
0.06
cene
0.06
[element
0.06
od
0.06
attle
0.06
derin
0.06
(Char
0.06
INTER
0.06
Activations Density 0.011%