INDEX
Explanations
mathematical or scientific notation and symbols
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.24
0.9%
1343
+0.13
0.5%
1978
+0.13
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1343
+0.24
0.06
453
+0.13
0.05
34
+0.13
0.04
Negative Logits
<bos>
-3.35
-0.91
ⓧ
-0.86
disbur
-0.81
<?
-0.79
/**
-0.75
/***
-0.68
acquaint
-0.65
ratify
-0.65
defray
-0.64
POSITIVE LOGITS
santiago
1.16
nomine
1.14
hcm
1.13
valencia
1.13
maroc
1.09
ricardo
1.09
alberto
1.05
guatemala
1.05
gonz
1.05
roberto
1.04
Activations Density 0.201%