INDEX
Explanations
mentions of schedules, daily activities, and busyness
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.29
1.1%
1013
+0.11
0.4%
1235
+0.08
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1013
+0.29
0.12
1235
+0.11
0.07
1317
+0.08
0.05
Negative Logits
<bos>
-2.44
enshr
-0.88
intersper
-0.85
vanqu
-0.84
endow
-0.83
underval
-0.74
rehabilitate
-0.72
/***
-0.72
incarcer
-0.71
disbur
-0.70
POSITIVE LOGITS
kaos
1.02
lele
1.01
bandung
0.98
churrasco
0.95
hany
0.89
indispensables
0.89
kebaya
0.88
palio
0.87
strass
0.86
capulco
0.86
Activations Density 2.166%