INDEX
Explanations
instances of the phrase "my name is" or variations of it
New Auto-Interp
Negative Logits
alcon
-0.16
нÑİ
-0.15
avigator
-0.15
omo
-0.15
icha
-0.15
addCriterion
-0.15
ikon
-0.15
upa
-0.14
ëħ¹
-0.14
unkt
-0.14
POSITIVE LOGITS
®
0.16
arda
0.15
Doyle
0.15
é϶
0.14
ľ
0.14
Milk
0.14
Ra
0.14
toast
0.13
suite
0.13
warfare
0.13
Activations Density 0.152%