INDEX
Explanations
phrases related to social issues and fundraising efforts
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1515
+0.15
0.5%
1491
+0.13
0.5%
1806
+0.13
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1515
+0.15
0.04
1806
+0.13
0.04
1565
+0.13
0.03
Negative Logits
décro
-0.60
Sne
-0.52
carrefour
-0.51
panik
-0.50
ralenti
-0.48
papillon
-0.48
Avez
-0.48
récla
-0.48
renfer
-0.46
moulin
-0.46
POSITIVE LOGITS
raise
1.29
raised
1.23
raising
1.19
raise
1.18
raises
1.17
Raise
1.16
raised
1.16
Raising
1.05
Raise
1.03
raising
1.01
Activations Density 0.099%