INDEX
Explanations
phrases related to sequences of events or actions
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
196
+0.08
0.2%
9
+0.08
0.2%
1790
+0.08
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
9
+0.08
0.03
1786
+0.08
0.01
196
+0.08
0.03
Negative Logits
Not
-0.42
frain
-0.41
совмести
-0.41
стероид
-0.41
ILogger
-0.40
OnDelete
-0.40
Binds
-0.40
Élet
-0.39
SNS
-0.39
bcryptjs
-0.39
POSITIVE LOGITS
stihl
0.89
bandung
0.89
kram
0.85
Minang
0.82
kark
0.81
abnorm
0.81
jawa
0.79
dises
0.79
jaya
0.79
finis
0.79
Activations Density 0.157%