INDEX
Explanations
the word "to" with varying strength
instances of the phrase "it’s hard to"
New Auto-Interp
Negative Logits
Conditions
-0.72
plates
-0.68
embodiments
-0.66
Flags
-0.65
items
-0.64
cand
-0.60
Votes
-0.60
faces
-0.59
Maker
-0.58
Sierra
-0.58
POSITIVE LOGITS
imagine
1.34
reconcile
1.30
quantify
1.25
distinguish
1.22
justify
1.20
convince
1.17
conceive
1.17
discern
1.15
differentiate
1.14
compare
1.13
Activations Density 0.074%