INDEX
Explanations
descriptions of various types of fantasy creatures and beings
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
2034
+0.14
0.4%
2019
+0.14
0.4%
1577
+0.14
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
195
+0.14
0.09
382
+0.14
0.09
359
+0.14
0.08
Negative Logits
leswig
-0.54
wußt
-0.52
Zwar
-0.52
supposed
-0.48
garcia
-0.48
rodriguez
-0.47
actually
-0.46
tabControl
-0.46
znacznie
-0.46
tortas
-0.45
POSITIVE LOGITS
circon
0.79
sopr
0.79
Wikisource
0.74
"}")
0.73
Wikiquote
0.73
profili
0.72
pendente
0.72
trion
0.70
itali
0.70
vider
0.70
Activations Density 0.572%