INDEX
Explanations
dates and locations associated with news events
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
411
+0.16
0.6%
421
+0.13
0.4%
950
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
411
+0.16
0.04
421
+0.13
0.03
587
+0.10
0.03
Negative Logits
Walkover
-0.67
archiviato
-0.65
LookAnd
-0.65
július
-0.65
octombrie
-0.65
noiembrie
-0.63
septembrie
-0.60
YECTO
-0.59
iulie
-0.59
decembrie
-0.58
POSITIVE LOGITS
indestru
1.20
waifu
1.19
strick
1.19
maneu
1.18
inconce
1.17
shenan
1.16
increa
1.16
hentai
1.15
wikihow
1.14
perfet
1.13
Activations Density 0.047%