INDEX
Explanations
references to competition and comparison among entities or subjects
New Auto-Interp
Negative Logits
king
-0.15
éré
-0.14
kin
-0.14
кÑĥ
-0.14
kins
-0.14
.boost
-0.14
á»ī
-0.14
keeper
-0.13
Corner
-0.13
ente
-0.13
POSITIVE LOGITS
other
0.53
others
0.43
other
0.43
åħ¶ä»ĸ
0.42
anderen
0.39
otros
0.38
OTHER
0.38
åħ¶ä»ĸ
0.37
others
0.37
altri
0.37
Activations Density 0.251%