INDEX
Explanations
dates in historical or legal contexts
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.16
0.9%
1978
+0.10
0.6%
1909
+0.08
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1978
+0.16
0.07
1527
+0.10
0.06
573
+0.08
0.05
Negative Logits
<bos>
-2.17
-0.84
/**
-0.82
/*
-0.74
ⓧ
-0.74
/***
-0.72
<?
-0.71
///**
-0.70
ുറ
-0.69
<?
-0.68
POSITIVE LOGITS
maneu
2.05
affor
1.97
increa
1.94
disagre
1.80
stockholm
1.80
accla
1.78
impra
1.77
excru
1.74
inev
1.74
reluct
1.71
Activations Density 0.201%