INDEX
Explanations
mentions of sports teams and competitions
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
764
+0.18
0.6%
1253
+0.16
0.6%
752
+0.14
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
764
+0.18
0.04
752
+0.16
0.03
16
+0.14
0.04
Negative Logits
.
-0.63
↵↵
-0.55
).
-0.54
!
-0.53
..
-0.52
...
-0.52
↵
-0.50
".
-0.50
».
-0.50
'.
-0.49
POSITIVE LOGITS
Joaqu
1.19
bandung
1.18
Mlle
1.17
Juf
1.17
ibiza
1.17
ecru
1.15
swarovski
1.13
affez
1.13
jorge
1.13
tenerife
1.11
Activations Density 0.172%