INDEX
Explanations
mentions related to government actions and policies, particularly in the context of police forces, the Sudanese government, textbooks in schools, and the racing industry
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1842
+0.16
0.5%
227
+0.15
0.5%
1150
+0.12
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
227
+0.16
0.10
1842
+0.15
0.08
1438
+0.12
0.06
Negative Logits
affez
-1.21
erec
-1.15
sappi
-1.12
Lmfao
-1.12
Hahah
-1.10
Ikr
-1.10
ftu
-1.08
fep
-1.07
eyel
-1.07
aen
-1.06
POSITIVE LOGITS
because
0.64
.
0.62
due
0.62
while
0.62
based
0.59
unless
0.58
;
0.57
optik
0.57
umacher
0.56
until
0.56
Activations Density 0.843%