INDEX
Explanations
mentions of the name "Anthony."
New Auto-Interp
Negative Logits
än
-0.15
ers
-0.15
GAN
-0.15
emer
-0.15
@student
-0.14
ersen
-0.14
Organic
-0.14
enie
-0.14
)((((
-0.14
eral
-0.14
POSITIVE LOGITS
Bour
0.24
Joshua
0.23
Martial
0.22
Weiner
0.22
Blink
0.20
Alban
0.20
bour
0.20
Hopkins
0.20
ony
0.19
bour
0.18
Activations Density 0.010%