INDEX
Explanations
team names and their matchups in sports contexts
New Auto-Interp
Negative Logits
ole
-0.17
ãĤĥ
-0.15
å¾ĭ
-0.15
олоÑģ
-0.14
ÑĥÑĪ
-0.14
dere
-0.14
Walters
-0.14
jen
-0.14
ágenes
-0.13
åĬŁ
-0.13
POSITIVE LOGITS
780
0.16
ray
0.15
oca
0.14
SCALL
0.14
nn
0.14
erty
0.14
Emerson
0.14
radix
0.14
اÙĨÙĪ
0.14
nos
0.14
Activations Density 0.019%