INDEX
Explanations
keywords related to video games and alternative universes
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
198
+0.15
0.4%
752
+0.14
0.4%
872
+0.13
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
198
+0.15
0.06
16
+0.14
0.06
752
+0.13
0.04
Negative Logits
titleMargin
-0.70
DockStyle
-0.59
HtmlAttribute
-0.58
("="-0.55
Điều
-0.55
Còn
-0.55
ECTION
-0.54
rente
-0.53
ChildScrollView
-0.53
<<<<<<<<<<<<<<
-0.52
POSITIVE LOGITS
carrefour
1.29
Souha
1.20
Sén
1.19
Docteur
1.15
triomphe
1.14
mépris
1.14
malheur
1.13
Traité
1.11
Mère
1.10
fameux
1.10
Activations Density 0.491%