INDEX
Explanations
phrases related to the search for extraterrestrial life
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
604
+0.10
0.3%
1042
+0.09
0.3%
674
+0.08
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
748
+0.10
0.01
1424
+0.09
0.03
1328
+0.08
0.03
Negative Logits
milano
-1.34
wien
-1.30
thermomix
-1.27
fluo
-1.25
casio
-1.25
hcm
-1.23
bordeaux
-1.22
NOO
-1.22
michelin
-1.19
levis
-1.19
POSITIVE LOGITS
would
1.11
would
0.98
Would
0.88
Would
0.87
WOULD
0.79
could
0.78
wouldn
0.75
will
0.68
if
0.67
wäre
0.65
Activations Density 0.236%