INDEX
Explanations
phrases related to legislative debates
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1499
+0.10
0.3%
1899
+0.09
0.3%
872
+0.09
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1864
+0.10
0.04
1860
+0.09
0.04
143
+0.09
0.05
Negative Logits
tupperware
-1.03
fluo
-1.00
ibiza
-0.96
bordeaux
-0.95
oleo
-0.94
trouva
-0.94
thermomix
-0.94
cannes
-0.92
swarovski
-0.90
Intere
-0.89
POSITIVE LOGITS
argue
0.97
argument
0.84
argues
0.84
argued
0.80
Arguments
0.78
arguments
0.77
argument
0.76
arguments
0.74
arguing
0.73
argumentos
0.71
Activations Density 0.445%