INDEX
Explanations
the word "notice" in various contexts
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
90
+0.13
0.5%
1983
+0.11
0.4%
1839
+0.10
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
90
+0.13
0.03
1370
+0.11
0.03
1839
+0.10
0.02
Negative Logits
affirme
-0.63
déclare
-0.62
défend
-0.59
souligne
-0.53
croit
-0.53
reconnaît
-0.52
prouve
-0.49
connaît
-0.47
préfère
-0.46
Sklici
-0.45
POSITIVE LOGITS
notice
1.18
notices
1.15
noticed
1.14
notice
1.09
Notice
1.08
noticing
1.07
noticed
1.06
Notice
1.03
notices
1.00
NOTICE
0.97
Activations Density 0.078%