INDEX
Explanations
instances of the phrase "like that"
phrases emphasizing the concept of "that."
New Auto-Interp
Negative Logits
istries
-0.81
oby
-0.69
orians
-0.66
ATURES
-0.66
brates
-0.66
ographies
-0.64
feet
-0.64
english
-0.64
IDES
-0.63
urs
-0.63
POSITIVE LOGITS
pesky
1.14
kind
0.82
cher
0.81
fateful
0.80
particular
0.76
elusive
0.75
sucker
0.74
equation
0.73
thing
0.73
aforementioned
0.73
Activations Density 0.084%