INDEX
Explanations
occurrences of the word "taught"
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.09
0.4%
9
+0.06
0.2%
341
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
769
+0.09
0.03
1743
+0.06
0.03
341
+0.05
0.03
Negative Logits
<bos>
-1.70
fillType
-0.74
public
-0.69
<?
-0.66
HasIndex
-0.63
else
-0.63
hline
-0.62
/***
-0.62
ੁ
-0.62
function
-0.61
POSITIVE LOGITS
maneu
1.97
accla
1.95
lidl
1.84
affor
1.82
stockholm
1.76
impra
1.73
wherea
1.72
shenan
1.70
excru
1.70
ibiza
1.69
Activations Density 0.059%