INDEX
Explanations
information related to media, specifically featuring Dracula and mentions in film related contexts
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
678
+0.18
0.5%
1403
+0.09
0.3%
1804
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
678
+0.18
0.06
64
+0.09
0.03
81
+0.09
0.01
Negative Logits
DeleteMapping
-0.59
ercice
-0.58
guangdong
-0.58
calorías
-0.58
primit
-0.56
scă
-0.56
"..\..\..\
-0.56
kedés
-0.56
tamaños
-0.56
împre
-0.55
POSITIVE LOGITS
unve
1.00
pamph
0.97
uniqu
0.97
contex
0.96
embra
0.95
resear
0.94
reluct
0.93
depic
0.93
indoc
0.93
compen
0.91
Activations Density 0.476%