INDEX
Explanations
phrases related to various combinations or choices
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1921
+0.10
0.3%
1133
+0.09
0.3%
197
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1971
+0.10
0.02
1921
+0.09
0.02
1368
+0.09
0.02
Negative Logits
Souha
-0.71
racon
-0.68
sobri
-0.65
Chapitre
-0.65
viciss
-0.63
coerci
-0.63
solidar
-0.63
Molto
-0.63
Membre
-0.63
Áng
-0.62
POSITIVE LOGITS
combination
1.06
combination
0.99
Combination
0.92
combinations
0.90
Combination
0.86
combinación
0.81
combinaison
0.79
combinations
0.77
combo
0.75
Kombination
0.75
Activations Density 0.080%