INDEX
Explanations
references to chess and related terms
New Auto-Interp
Negative Logits
bondale
-0.39
Larkin
-0.39
Yuen
-0.39
Local
-0.37
local
-0.37
Lipa
-0.37
from
-0.37
Local
-0.36
Guido
-0.36
Moffat
-0.36
POSITIVE LOGITS
chess
2.44
Chess
2.31
Chess
2.05
chess
1.81
ajedrez
1.49
棋
1.20
xadrez
1.16
Schach
1.12
edrez
1.11
poker
0.91
Activations Density 0.002%