INDEX
Explanations
the word "particular."
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1265
+0.13
0.5%
893
+0.13
0.5%
1994
+0.12
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1994
+0.13
0.03
893
+0.13
0.03
1265
+0.12
0.03
Negative Logits
depic
-0.78
compréhen
-0.74
resear
-0.74
!...
-0.71
mikrofon
-0.70
intitulée
-0.69
Pamph
-0.69
montrant
-0.69
fantaisie
-0.68
oks
-0.67
POSITIVE LOGITS
particular
1.19
particular
1.03
Particular
0.85
PARTICULAR
0.82
Particular
0.82
ticularly
0.74
specific
0.73
particulars
0.72
particolare
0.69
particulares
0.67
Activations Density 0.058%