INDEX
Explanations
phrases related to legal proceedings and announcements
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1499
+0.09
0.3%
344
+0.09
0.3%
514
+0.08
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
514
+0.09
0.03
1499
+0.09
0.05
247
+0.08
0.04
Negative Logits
!...
-1.30
?...
-1.27
effe
-1.25
ftu
-1.21
perfet
-1.21
increa
-1.19
indestru
-1.19
inconce
-1.19
nece
-1.18
unwarran
-1.18
POSITIVE LOGITS
verdict
0.66
decision
0.64
whether
0.63
tomorrow
0.63
decide
0.61
decisions
0.60
externi
0.59
whether
0.59
deciding
0.58
decision
0.56
Activations Density 0.379%