INDEX
Explanations
mentions of the name "Yuri"
occurrences of the term "uri" and variations, indicating it detects references to URLs or web resources
New Auto-Interp
Negative Logits
work
-0.71
rooms
-0.69
oak
-0.68
orative
-0.66
avis
-0.65
inosaur
-0.65
Barkley
-0.65
eenth
-0.64
Merrill
-0.64
eatures
-0.64
POSITIVE LOGITS
uri
1.16
Äĩ
0.94
qi
0.92
URI
0.90
witz
0.86
veyard
0.86
geon
0.85
ascus
0.83
uces
0.79
cia
0.79
Activations Density 0.008%