INDEX
Explanations
mentions of the name "Ted" and its variations
New Auto-Interp
Negative Logits
ivor
-0.17
lish
-0.16
inding
-0.15
ping
-0.15
_HAL
-0.15
etler
-0.14
eldom
-0.14
elda
-0.14
Hardware
-0.14
olik
-0.14
POSITIVE LOGITS
dy
0.30
Bundy
0.21
esco
0.21
dy
0.20
ious
0.19
IOUS
0.19
di
0.19
isco
0.18
dyn
0.18
DY
0.17
Activations Density 0.007%