INDEX
Explanations
words and phrases related to expressions of dismissal or indifference
expressions of resignation or indifference
New Auto-Interp
Negative Logits
cycl
-0.83
wives
-0.74
eve
-0.72
jun
-0.69
teenth
-0.69
nel
-0.68
port
-0.67
scape
-0.67
listed
-0.66
etr
-0.66
POSITIVE LOGITS
shrug
1.33
grin
0.92
sigh
0.92
bask
0.82
laughter
0.79
smile
0.78
nods
0.77
chuckle
0.77
frown
0.77
relax
0.76
Activations Density 0.024%