INDEX
Explanations
phrases related to shutting something down or up
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1328
+0.15
0.6%
663
+0.14
0.5%
544
+0.12
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
663
+0.15
0.03
1328
+0.14
0.03
544
+0.12
0.02
Negative Logits
Xoa
-0.56
Kanna
-0.53
beque
-0.52
Tole
-0.51
Ili
-0.50
Pé
-0.49
OI
-0.49
Pli
-0.48
AEG
-0.48
Qar
-0.48
POSITIVE LOGITS
shut
1.43
Shut
1.27
shut
1.27
Shut
1.23
SHUT
1.17
shuts
1.13
SHUT
1.12
shutting
1.09
shutdown
0.99
shutdown
0.94
Activations Density 0.068%