INDEX
Explanations
words related to international conflicts and diplomatic negotiations
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
75
+0.11
0.3%
2041
+0.08
0.2%
1485
+0.07
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
809
+0.11
0.04
75
+0.08
0.02
837
+0.07
0.02
Negative Logits
impra
-1.48
reluct
-1.41
maneu
-1.35
increa
-1.34
affor
-1.31
shenan
-1.24
purcha
-1.23
wherea
-1.22
strick
-1.21
scrat
-1.21
POSITIVE LOGITS
hornblende
0.59
cault
0.55
phorbia
0.52
phazard
0.51
diali
0.50
հղումներ
0.50
Jornal
0.50
wild
0.50
biotite
0.49
lapsingToolbar
0.49
Activations Density 0.254%