INDEX
Explanations
occurrences of the word "of" representing a specific grammatical usage
New Auto-Interp
Negative Logits
iaux
-0.15
ays
-0.15
631
-0.14
sov
-0.14
ging
-0.14
ING
-0.14
mgr
-0.14
meric
-0.13
ilmington
-0.13
Ai
-0.13
POSITIVE LOGITS
efon
0.17
VERR
0.15
ONES
0.15
luet
0.14
isos
0.14
oley
0.14
AMI
0.14
optera
0.14
vie
0.14
ôt
0.14
Activations Density 0.019%