INDEX
Explanations
names and titles of characters in a specific franchise
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
453
+0.14
0.4%
1079
+0.12
0.4%
137
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
453
+0.14
0.01
649
+0.12
0.01
1831
+0.10
0.01
Negative Logits
fta
-1.43
thut
-1.33
Juf
-1.32
ftu
-1.31
ftre
-1.26
volunte
-1.26
Traité
-1.21
mef
-1.19
encomp
-1.18
makro
-1.17
POSITIVE LOGITS
商品説明
0.73
simplifié
0.63
VIAF
0.56
EndInit
0.56
تقاوى
0.55
ویکیپدیا
0.54
KURZBESCHREIBUNG
0.53
PerformLayout
0.53
setVerticalGroup
0.52
NSCoder
0.52
Activations Density 0.016%