INDEX
Explanations
names and surnames of individuals, particularly focusing on those with notable recognition or context in various situations
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1994
+0.15
0.9%
1464
+0.15
0.9%
1406
+0.14
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1994
+0.15
0.04
1056
+0.15
0.04
1343
+0.14
0.05
Negative Logits
<bos>
-1.40
intersper
-0.84
ethene
-0.69
Referencie
-0.69
ötä
-0.68
Více
-0.65
apprehen
-0.65
quitted
-0.64
ⓧ
-0.63
trod
-0.62
POSITIVE LOGITS
dy
1.02
Wy
1.02
Dy
0.99
Wy
0.97
Ry
0.96
RY
0.96
DY
0.94
Gy
0.93
Dys
0.93
dy
0.92
Activations Density 0.206%