INDEX
Explanations
mentions of the name "Ken" or variations of it
New Auto-Interp
Negative Logits
erm
-0.17
TestCategory
-0.15
cea
-0.15
_ABI
-0.14
lant
-0.14
erot
-0.14
ceasefire
-0.14
Wunused
-0.14
birthdate
-0.13
bes
-0.13
POSITIVE LOGITS
yon
0.30
yan
0.29
ya
0.23
elm
0.23
zie
0.23
rick
0.23
itra
0.23
aston
0.22
worthy
0.22
mare
0.22
Activations Density 0.009%