INDEX
Explanations
mentions of the word "Virgin" in various contexts
New Auto-Interp
Negative Logits
erro
-0.17
drs
-0.17
aar
-0.17
avanaugh
-0.16
ernen
-0.16
kowski
-0.15
resden
-0.15
dog
-0.15
raman
-0.15
Jens
-0.15
POSITIVE LOGITS
Atlantic
0.35
Galactic
0.32
Atlantic
0.27
Islands
0.23
Voy
0.23
atl
0.23
Orbit
0.21
America
0.21
ity
0.20
Money
0.20
Activations Density 0.003%