INDEX
Explanations
names and titles related to sports and education
New Auto-Interp
Negative Logits
.↵
-0.21
.↵↵
-0.20
,↵
-0.20
ãĢĤ↵
-0.20
,↵↵
-0.17
;↵
-0.17
;↵↵
-0.16
).↵
-0.15
?↵
-0.15
:↵↵
-0.14
POSITIVE LOGITS
,
0.24
Jr
0.21
ová
0.21
's
0.19
m
0.19
III
0.19
:,
0.17
),
0.17
',
0.17
â̬
0.17
Activations Density 0.018%