INDEX
Explanations
the word "first" in sentences
the phrase "at first" in various contexts
New Auto-Interp
Negative Logits
illed
-0.75
ux
-0.75
STEM
-0.70
raped
-0.68
inf
-0.68
die
-0.67
ged
-0.66
yet
-0.66
ourge
-0.64
gerald
-0.64
POSITIVE LOGITS
glance
1.41
blush
1.23
responders
0.94
sight
0.88
premise
0.84
instinct
0.77
impression
0.75
hurdle
0.75
glimpse
0.72
inclination
0.71
Activations Density 0.026%