INDEX
Explanations
phrases with the word "also," but it also appears to target specific informational details from varied content sources
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
172
+0.16
0.6%
645
+0.13
0.5%
228
+0.13
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
172
+0.16
0.08
645
+0.13
0.07
228
+0.13
0.06
Negative Logits
karton
-0.88
utop
-0.78
sement
-0.77
territo
-0.76
hunde
-0.74
silikon
-0.73
lemp
-0.71
solidar
-0.71
kosme
-0.70
keramik
-0.69
POSITIVE LOGITS
also
0.80
also
0.78
ALSO
0.71
también
0.67
Also
0.66
também
0.65
Also
0.62
también
0.62
også
0.60
juga
0.59
Activations Density 0.251%