INDEX
Explanations
references to the person "Taylor Swift."
mentions of the name "Taylor" and "Taylor Swift."
New Auto-Interp
Negative Logits
rontal
-0.94
PDATE
-0.90
oard
-0.87
undai
-0.85
hemy
-0.79
ntil
-0.75
pread
-0.73
cffffcc
-0.73
iltration
-0.73
vous
-0.72
POSITIVE LOGITS
Made
1.14
Swift
1.04
obi
0.83
Taylor
0.76
ville
0.73
hurst
0.71
folk
0.70
Nichols
0.69
ual
0.69
Bean
0.69
Activations Density 0.030%