INDEX
Explanations
words related to sports or physical objects such as balls
references to "ball" in various contexts
New Auto-Interp
Negative Logits
ä
-0.69
éĥ
-0.68
ä½ľ
-0.68
Equality
-0.65
åİ
-0.65
éĸ
-0.63
ãĥ´
-0.63
ETH
-0.63
LY
-0.62
Income
-0.60
POSITIVE LOGITS
istics
1.07
oons
1.03
ball
0.98
oon
0.95
ozo
0.93
park
0.87
asted
0.87
ast
0.87
assic
0.87
istically
0.86
Activations Density 0.012%