INDEX
Explanations
references to the name "Ted"
mentions of the name "Ted."
New Auto-Interp
Negative Logits
ebin
-0.73
unseen
-0.68
upkeep
-0.63
[*
-0.63
Spoiler
-0.61
cx
-0.61
discipl
-0.59
ingred
-0.59
sshd
-0.58
decay
-0.57
POSITIVE LOGITS
Cruz
1.16
Cruz
1.13
Bundy
0.87
sson
0.87
Nug
0.86
iosity
0.84
der
0.83
icates
0.82
gers
0.80
chers
0.79
Activations Density 0.011%