INDEX
Explanations
phrases related to politics and government actions
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
604
+0.13
0.4%
344
+0.10
0.3%
378
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
344
+0.13
0.03
1499
+0.10
0.05
915
+0.09
0.04
Negative Logits
swarovski
-1.82
embodi
-1.81
ecru
-1.70
increa
-1.65
impra
-1.65
affor
-1.64
scrat
-1.63
indestru
-1.63
hairc
-1.59
encomp
-1.58
POSITIVE LOGITS
ValueStyle
0.70
ContentAsync
0.69
Imágenes
0.68
Cyfarwyddwr
0.68
FBref
0.67
autorytatywna
0.66
mergeFrom
0.65
ibatis
0.65
Mí
0.65
smithy
0.65
Activations Density 0.364%