INDEX
Explanations
terms and phrases related to the beauty and hair industry
New Auto-Interp
Negative Logits
icter
-0.15
ania
-0.14
.Serve
-0.14
rica
-0.14
å¾½
-0.14
оÑī
-0.13
utin
-0.13
ãĥ©ãĥĥãĤ¯
-0.13
urdy
-0.13
mland
-0.13
POSITIVE LOGITS
salon
0.37
Salon
0.35
hair
0.32
beauty
0.31
hair
0.31
hairst
0.31
Hair
0.30
Beauty
0.28
Hair
0.28
sty
0.27
Activations Density 0.048%