INDEX
Explanations
the word "crew" in various contexts
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
506
+0.13
0.5%
1516
+0.12
0.5%
1573
+0.12
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1573
+0.13
0.02
506
+0.12
0.02
1516
+0.12
0.02
Negative Logits
diable
-0.44
vlas
-0.44
bâton
-0.43
contente
-0.43
phorbia
-0.43
suspendu
-0.43
Sait
-0.42
Balan
-0.42
Palme
-0.42
Kand
-0.41
POSITIVE LOGITS
crew
1.36
crew
1.31
Crew
1.30
Crew
1.26
crews
1.21
Crews
1.09
CRE
0.69
cre
0.66
cre
0.65
Cre
0.65
Activations Density 0.087%