INDEX
Explanations
statements about political or military actions and events
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1741
+0.13
0.4%
2019
+0.13
0.4%
1445
+0.12
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
382
+0.13
0.05
1162
+0.13
0.04
1265
+0.12
0.04
Negative Logits
étend
-1.07
prétend
-1.06
bonté
-1.05
réal
-1.03
renfer
-1.03
Outils
-1.02
prédé
-1.02
rafra
-1.01
Décembre
-1.01
sappi
-1.01
POSITIVE LOGITS
finding
0.63
we
0.61
there
0.60
perhaps
0.57
attention
0.57
opportunities
0.55
hopefully
0.55
many
0.55
questions
0.54
it
0.54
Activations Density 0.282%