INDEX
Explanations
words related to options or alternatives
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.14
0.6%
1872
+0.06
0.2%
1110
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1110
+0.14
0.05
1243
+0.06
0.05
868
+0.05
0.05
Negative Logits
<bos>
-1.99
public
-0.86
Descripció
-0.75
export
-0.73
cshtml
-0.71
/**
-0.69
-0.69
void
-0.68
Referències
-0.67
continue
-0.67
POSITIVE LOGITS
stockholm
2.12
affor
2.10
maneu
2.09
accla
2.04
impra
2.02
Juf
1.98
fta
1.98
volunte
1.98
increa
1.95
philanth
1.94
Activations Density 0.084%