INDEX
Explanations
mentions of the name "Juan"
New Auto-Interp
Negative Logits
kud
-0.17
kim
-0.15
065
-0.15
yal
-0.15
IAS
-0.15
nung
-0.14
chalk
-0.14
WithEmail
-0.14
ijk
-0.14
versible
-0.14
POSITIVE LOGITS
ita
0.27
cho
0.23
Pablo
0.23
Carlos
0.22
ITA
0.20
jo
0.20
itas
0.19
Antonio
0.17
ito
0.17
Carlos
0.16
Activations Density 0.006%