INDEX
Explanations
terms related to sports plays and actions
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.17
0.6%
1842
+0.09
0.3%
1905
+0.07
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1905
+0.17
0.04
1290
+0.09
0.03
736
+0.07
0.03
Negative Logits
<bos>
-2.11
/***
-0.64
/**
-0.59
peintures
-0.57
prêtres
-0.56
-0.56
public
-0.54
<?
-0.54
defray
-0.53
/*
-0.52
POSITIVE LOGITS
Minang
1.07
véhic
0.98
silikon
0.89
applau
0.88
Banjar
0.86
Guanajuato
0.86
electrica
0.84
Portugu
0.84
Minangkabau
0.84
karton
0.83
Activations Density 0.095%