INDEX
Explanations
occurrences of the name "Dan" and its variations
New Auto-Interp
Negative Logits
yu
-0.20
gow
-0.18
yat
-0.17
yor
-0.17
eln
-0.17
yd
-0.16
ownt
-0.15
kidding
-0.15
ptal
-0.15
chan
-0.15
POSITIVE LOGITS
iele
0.36
ilo
0.33
ube
0.29
vers
0.27
zig
0.27
bury
0.26
forth
0.25
ial
0.25
ield
0.24
Ä±ÅŁman
0.24
Activations Density 0.007%