INDEX
Negative Logits
,
1.39
?
1.17
/
1.16
!
1.07
-
1.07
(
1.00
:
0.99
%
0.97
"
0.89
.
0.88
POSITIVE LOGITS
restaurants
1.40
functions
1.40
human
1.36
im
1.36
horm
1.35
breeds
1.35
def
1.34
manip
1.33
stands
1.33
za
1.33
Activations Density 0.000%
,
?
/
!
-
(
:
%
"
.
restaurants
functions
human
im
horm
breeds
def
manip
stands
za