INDEX
Explanations
This neuron activates on the indefinite article “an.”
New Auto-Interp
Negative Logits
ñana
-0.06
Cheese
-0.06
yoktur
-0.06
것
-0.06
fries
-0.06
truyền
-0.06
convex
-0.06
dbName
-0.06
lợi
-0.06
asename
-0.06
POSITIVE LOGITS
ст
0.07
grids
0.06
_MARGIN
0.06
ing
0.06
abruptly
0.06
anson
0.06
fascinated
0.06
та
0.06
баг
0.06
مساحت
0.06
Activations Density 0.032%