INDEX
Explanations
terms related to sports teams and competitions
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.19
0.9%
757
+0.17
0.8%
481
+0.10
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
757
+0.19
0.07
1974
+0.17
0.04
699
+0.10
0.04
Negative Logits
<bos>
-3.43
/***
-0.69
<>
-0.65
and
-0.65
to
-0.64
<!--
-0.63
//};
-0.63
be
-0.63
.
-0.62
introduce
-0.62
POSITIVE LOGITS
bandung
1.63
Minang
1.53
Juf
1.48
meis
1.47
Karang
1.47
wien
1.46
stockholm
1.45
accla
1.42
lele
1.41
ananas
1.40
Activations Density 0.149%