INDEX
Explanations
mentions of occasions or events being celebrated
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1145
+0.16
0.5%
1065
+0.15
0.5%
900
+0.14
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1065
+0.16
0.03
900
+0.15
0.03
1145
+0.14
0.03
Negative Logits
unhofer
-0.66
ApiProperty
-0.64
FetchType
-0.61
Atsauces
-0.61
JsonKey
-0.59
himo
-0.59
InputModule
-0.58
Algunas
-0.58
Để
-0.58
estekak
-0.57
POSITIVE LOGITS
unspeak
1.60
maneu
1.55
impra
1.54
increa
1.51
intersper
1.49
snoopy
1.46
depic
1.41
gaily
1.39
scrat
1.38
shenan
1.37
Activations Density 0.076%