INDEX
Explanations
details about a person's biography or life events
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
453
+0.10
0.3%
163
+0.09
0.3%
184
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1038
+0.10
0.04
382
+0.09
0.05
1136
+0.09
0.05
Negative Logits
mef
-1.18
aen
-1.16
wien
-1.16
maer
-1.15
oleo
-1.15
uncin
-1.12
napoli
-1.10
meis
-1.10
milano
-1.10
ohr
-1.10
POSITIVE LOGITS
<bos>
0.97
subsequently
0.65
participated
0.64
later
0.64
thereafter
0.63
became
0.60
then
0.60
contributed
0.60
earned
0.59
successfully
0.59
Activations Density 0.530%