INDEX
Explanations
words related to a specific location, Rio de Janeiro
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
2011
+0.12
0.4%
1103
+0.09
0.2%
1350
+0.08
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1120
+0.12
0.02
1656
+0.09
0.02
1721
+0.08
0.02
Negative Logits
直
-0.70
“
-0.69
appear
-0.69
for
-0.69
га
-0.69
необходимость
-0.68
fix
-0.68
各
-0.68
can
-0.68
ли
-0.67
POSITIVE LOGITS
Rio
2.35
Rio
2.18
RIO
2.14
affor
2.09
accla
1.94
increa
1.92
embodi
1.85
fta
1.84
stockholm
1.84
unden
1.81
Activations Density 0.191%