INDEX
Explanations
instances of the phrase "of course" within text
phrases that include the term "of course"
New Auto-Interp
Negative Logits
erd
-0.76
ELD
-0.68
ements
-0.66
ige
-0.63
ellen
-0.62
downt
-0.59
ITCH
-0.57
rison
-0.57
Northwest
-0.54
ments
-0.54
POSITIVE LOGITS
mouth
0.83
milo
0.74
forth
0.72
trump
0.72
ulla
0.69
ushima
0.68
promptly
0.65
tyr
0.64
mosqu
0.63
washer
0.63
Activations Density 0.037%