INDEX
Explanations
specific historical or geographical references
New Auto-Interp
Negative Logits
bay
-0.20
Bay
-0.19
cal
-0.17
bay
-0.17
jango
-0.17
Bay
-0.17
TF
-0.16
Santana
-0.16
tf
-0.15
Monte
-0.15
POSITIVE LOGITS
cro
0.20
cro
0.20
Cros
0.20
Cro
0.19
Cro
0.18
Ky
0.17
Ky
0.17
Crop
0.16
imos
0.16
erez
0.16
Activations Density 0.037%