INDEX
Explanations
names of people within the text
New Auto-Interp
Negative Logits
dég
-0.43
tagHelperRunner
-0.42
Aldo
-0.41
Jonathan
-0.41
Jonathan
-0.38
inalámbrica
-0.37
médicale
-0.37
Larry
-0.36
asce
-0.35
Vezi
-0.35
POSITIVE LOGITS
ina
0.57
ena
0.54
ilda
0.53
ette
0.53
ita
0.52
vina
0.52
wenn
0.50
leen
0.49
trude
0.49
cie
0.48
Activations Density 0.212%