INDEX
Explanations
nouns and their variations
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
156
+0.28
1.6%
497
+0.13
0.7%
146
+0.12
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
329
+0.28
0.05
353
+0.13
0.07
276
+0.12
0.06
Negative Logits
CIAL
-1.51
:`
-1.50
climbed
-1.47
ção
-1.42
^](#
-1.37
sung
-1.32
igm
-1.30
"—
-1.30
meant
-1.29
fined
-1.26
POSITIVE LOGITS
istor
1.40
apart
1.39
?).
1.36
pathogen
1.34
adjuvant
1.33
Portal
1.33
GV
1.33
advantages
1.32
posts
1.32
portal
1.31
Activations Density 0.501%