INDEX
Explanations
phrases related to interviews or press tours in the entertainment industry
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
184
+0.40
1.6%
764
+0.39
1.5%
1343
+0.19
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
764
+0.40
0.01
184
+0.39
0.01
1784
+0.19
0.01
Negative Logits
Италијани
-0.65
Vitamina
-0.62
sopr
-0.58
volantes
-0.56
vitamine
-0.56
/***
-0.55
poliuret
-0.54
<bos>
-0.54
/**
-0.52
Witam
-0.51
POSITIVE LOGITS
shenan
0.73
apprehen
0.68
intersper
0.67
unspeak
0.62
disreg
0.61
artifice
0.60
disambigu
0.59
ineffec
0.56
shuddered
0.56
cushi
0.56
Activations Density 0.008%