INDEX
Explanations
details related to a specific video game, including characters, gameplay features, and setting
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
304
+0.10
0.3%
334
+0.09
0.3%
50
+0.08
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1551
+0.10
0.04
792
+0.09
0.03
441
+0.08
0.04
Negative Logits
territo
-0.79
dises
-0.76
Keny
-0.75
Muhamma
-0.70
tolu
-0.70
Juf
-0.69
déploy
-0.68
saar
-0.67
maksi
-0.67
Abbé
-0.66
POSITIVE LOGITS
customizable
0.59
customize
0.56
interact
0.52
gameplay
0.52
customization
0.50
uLocal
0.50
explore
0.50
choose
0.49
immerse
0.49
character
0.49
Activations Density 0.476%