INDEX
Explanations
references to specific names, particularly variations of the name "Gary."
New Auto-Interp
Negative Logits
Lilly
-0.56
Jem
-0.55
Rose
-0.53
Nat
-0.53
valentino
-0.53
htë
-0.52
ना
-0.51
Oli
-0.50
Liv
-0.50
κος
-0.50
POSITIVE LOGITS
Gary
1.26
Gary
1.24
Karen
1.14
Kathy
1.13
Linda
1.10
Kathy
1.09
Lori
1.08
Linda
1.08
Lori
1.08
Karen
1.05
Activations Density 0.154%