INDEX
Explanations
phrases related to legal and technical document content
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
752
+0.10
0.4%
1120
+0.10
0.4%
823
+0.06
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
752
+0.10
0.17
1120
+0.10
0.16
823
+0.06
0.15
Negative Logits
also
-1.24
now
-1.21
have
-1.20
could
-1.19
even
-1.19
in
-1.19
for
-1.18
.
-1.18
might
-1.17
may
-1.17
POSITIVE LOGITS
stockholm
3.17
wien
3.12
vété
2.90
?...
2.89
Juf
2.85
mef
2.84
véhic
2.84
délib
2.83
accla
2.82
„,
2.81
Activations Density 1.626%