INDEX
Explanations
mentions of individuals associated with specific sports or professions
New Auto-Interp
Negative Logits
pardon
-0.15
nod
-0.14
uche
-0.14
acle
-0.14
_strerror
-0.14
оÑģÑĤав
-0.14
imore
-0.14
Pentagon
-0.13
ECT
-0.13
usra
-0.13
POSITIVE LOGITS
geist
0.15
roupon
0.15
ipop
0.14
Fundamental
0.14
oucher
0.13
relieved
0.13
edback
0.13
772
0.13
_();↵
0.13
omp
0.12
Activations Density 0.008%