INDEX
Explanations
references to Disney pop culture and themed outfits
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
198
+0.15
0.5%
872
+0.15
0.4%
764
+0.13
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2007
+0.15
0.04
764
+0.15
0.05
198
+0.13
0.06
Negative Logits
DockStyle
-0.59
Viited
-0.56
ECONDS
-0.55
ItemBackground
-0.55
Tetrach
-0.55
Trichlor
-0.55
ChildScrollView
-0.55
windowFixed
-0.54
MessageTagHelper
-0.54
medades
-0.53
POSITIVE LOGITS
Docteur
0.91
Sén
0.90
indestru
0.83
Messieurs
0.81
inconce
0.78
négoci
0.75
trouva
0.74
indoc
0.74
indescri
0.74
emphat
0.73
Activations Density 0.799%