INDEX
Explanations
names and entities related to sports and entertainment figures
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1177
+0.22
0.8%
1842
+0.14
0.5%
964
+0.12
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1177
+0.22
0.05
1741
+0.14
0.02
283
+0.12
0.03
Negative Logits
<bos>
-2.73
.
-0.97
<eos>
-0.93
and
-0.92
,
-0.90
for
-0.90
in
-0.90
at
-0.88
on
-0.88
if
-0.88
POSITIVE LOGITS
lele
2.35
alkoh
2.33
dises
2.32
kram
2.31
mef
2.29
cannes
2.28
wien
2.28
embra
2.22
stockholm
2.22
milano
2.22
Activations Density 0.768%