INDEX
Explanations
occurrences of the article "an" and the word "the"
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
74
+0.13
0.7%
222
+0.12
0.7%
98
+0.12
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
222
+0.13
0.02
74
+0.12
0.01
371
+0.12
0.02
Negative Logits
headlines
-1.80
tig
-1.74
Figure
-1.64
conversions
-1.57
respectively
-1.53
cursors
-1.40
starters
-1.40
medalists
-1.40
valence
-1.36
fans
-1.34
POSITIVE LOGITS
sible
1.72
revoked
1.65
blinded
1.44
expired
1.43
renewal
1.41
·
1.41
domain
1.40
grant
1.37
unrelated
1.36
revocation
1.36
Activations Density 0.028%