INDEX
Explanations
phrases indicating anticipation or excitement
expressions of anticipation or eagerness
New Auto-Interp
Negative Logits
rant
-0.67
iosyncr
-0.66
Tibet
-0.63
mt
-0.62
edom
-0.62
constitution
-0.62
esm
-0.61
threat
-0.60
uneven
-0.59
viol
-0.59
POSITIVE LOGITS
patiently
0.84
anymore
0.77
eagerly
0.74
waiting
0.68
wait
0.68
poke
0.65
Discuss
0.64
seeing
0.63
yours
0.63
âĶľ
0.62
Activations Density 0.023%