INDEX
Explanations
names or titles prefixed with 'Sir'
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
645
+0.17
0.9%
50
+0.12
0.6%
555
+0.11
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
645
+0.17
0.03
1677
+0.12
0.02
1404
+0.11
0.02
Negative Logits
<bos>
-2.46
ⓧ
-0.74
<?
-0.67
/*++
-0.66
lateinit
-0.62
hline
-0.61
Παραπομπές
-0.61
poveznice
-0.58
-0.57
<!--
-0.57
POSITIVE LOGITS
Sir
1.47
Sir
1.44
sir
1.32
SIR
1.28
délib
1.19
SIR
1.14
véhic
1.13
sir
1.09
bayern
1.09
sergio
1.09
Activations Density 0.121%