INDEX
Explanations
verbs in the infinitive form
the phrase "to be" in various contexts
New Auto-Interp
Negative Logits
yip
-0.73
iasco
-0.71
Bucks
-0.66
fray
-0.65
wi
-0.64
itory
-0.61
Ferr
-0.60
antry
-0.60
Hav
-0.59
issance
-0.59
POSITIVE LOGITS
honest
1.42
frank
1.29
blunt
1.27
sure
1.26
fair
1.23
precise
1.22
truthful
1.16
clear
1.15
perfectly
1.11
exact
1.03
Activations Density 0.034%