INDEX
Explanations
phrases related to financial matters and taxation
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
764
+0.17
0.5%
1577
+0.14
0.5%
1108
+0.13
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
16
+0.17
0.07
764
+0.14
0.04
761
+0.13
0.04
Negative Logits
Sén
-0.93
Sénat
-0.92
Messieurs
-0.92
Souha
-0.91
Mlle
-0.89
poichè
-0.87
Mère
-0.87
Gouvernement
-0.87
Şi
-0.86
Docteur
-0.85
POSITIVE LOGITS
Himo
0.54
useCallback
0.48
overall
0.48
enderror
0.48
ORETICAL
0.48
.
0.46
EoL
0.45
%).
0.45
SneakyThrows
0.44
effective
0.43
Activations Density 0.533%