INDEX
Explanations
the word "first" occurring in a sentence
the phrase "At first" emphasizing initial actions or impressions
New Auto-Interp
Negative Logits
ux
-0.75
illed
-0.69
gerald
-0.69
raped
-0.68
zsche
-0.67
ourge
-0.66
Canaver
-0.66
vance
-0.65
die
-0.65
STEM
-0.64
POSITIVE LOGITS
glance
1.47
blush
1.34
sight
0.98
responders
0.85
Sight
0.79
premise
0.78
hesitant
0.77
stages
0.73
acle
0.71
baseman
0.68
Activations Density 0.021%