INDEX
Explanations
references to a specific brand or product named "BLU."
repeated references to a specific brand or product
New Auto-Interp
Negative Logits
FontSize
-0.71
Ãī
-0.69
oter
-0.66
tu
-0.66
agy
-0.63
Widget
-0.63
andise
-0.62
ocene
-0.60
enna
-0.60
uries
-0.60
POSITIVE LOGITS
BL
3.55
Bl
1.72
BL
1.62
Bl
1.62
bl
1.38
RED
1.33
bl
1.33
Blaze
1.25
GREEN
1.22
BLACK
1.21
Activations Density 0.013%