INDEX
Explanations
references to religious and biblical concepts and figures
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1842
+0.15
0.4%
509
+0.14
0.4%
2015
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
509
+0.15
0.05
1380
+0.14
0.01
1446
+0.09
0.02
Negative Logits
churrasco
-0.90
felicity
-0.72
seaborn
-0.70
pican
-0.68
liberality
-0.64
Silurian
-0.62
tolerably
-0.61
benevol
-0.61
idolat
-0.61
sacerd
-0.60
POSITIVE LOGITS
Și
0.57
Dacă
0.56
Să
0.53
Legături
0.52
memcmp
0.51
Referències
0.50
decembrie
0.50
saida
0.50
Schriften
0.49
Etimo
0.49
Activations Density 0.203%