INDEX
Explanations
ingredients and instructions for baking bread
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
876
+0.16
0.5%
1150
+0.11
0.3%
736
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
736
+0.16
0.04
1284
+0.11
0.02
4
+0.10
0.02
Negative Logits
gubern
-0.65
monaster
-0.64
Senat
-0.61
Presidencia
-0.57
Jurist
-0.57
Rumania
-0.56
Legislat
-0.56
ratific
-0.55
Psicología
-0.54
disambiguazione
-0.53
POSITIVE LOGITS
scrat
0.94
increa
0.92
affor
0.90
hasbro
0.90
perfet
0.87
stickied
0.85
wikihow
0.85
embodi
0.85
FFFF
0.84
snoopy
0.83
Activations Density 0.078%