INDEX
Explanations
references to a specific character or TV show, "SpongeBob SquarePants."
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1842
+0.12
0.3%
964
+0.11
0.3%
1533
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
981
+0.12
0.08
964
+0.11
0.04
1307
+0.09
0.03
Negative Logits
karbon
-0.69
silikon
-0.67
maksi
-0.64
المعيارى
-0.63
hunde
-0.61
akut
-0.59
akku
-0.58
uhr
-0.58
nawr
-0.58
onViewCreated
-0.56
POSITIVE LOGITS
indestru
0.79
anthrop
0.64
royaume
0.63
adorable
0.59
Nickelodeon
0.57
cute
0.56
mischievous
0.56
kinderg
0.55
Kindergarten
0.55
cartoons
0.55
Activations Density 0.870%