INDEX
Explanations
terms related to information technology (IT) concepts and technological processes
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.13
0.4%
1533
+0.09
0.3%
1819
+0.08
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1533
+0.13
0.03
16
+0.09
0.06
826
+0.08
0.03
Negative Logits
Abbé
-1.13
tremb
-1.00
embra
-1.00
deleter
-0.99
fta
-0.98
uniqu
-0.96
unve
-0.93
fto
-0.91
unden
-0.91
Shakspeare
-0.91
POSITIVE LOGITS
each
0.66
whereby
0.63
someone
0.61
Geplaatst
0.60
whenever
0.59
individuals
0.57
instead
0.56
individual
0.55
somebody
0.55
you
0.55
Activations Density 0.559%