INDEX
Explanations
occurrences of the phrase "the first time"
New Auto-Interp
Negative Logits
haar
-0.73
ouk
-0.71
ourt
-0.68
ebted
-0.66
urat
-0.66
oll
-0.64
uala
-0.64
fingert
-0.62
unit
-0.61
otto
-0.61
POSITIVE LOGITS
frame
0.70
frames
0.69
lapse
0.67
imester
0.65
around
0.62
ħĭ
0.62
seeing
0.60
capsule
0.60
EVER
0.60
round
0.60
Activations Density 0.418%