INDEX
Explanations
words related to hearing or listening
gerunds and present participles ending in 'ing' and 'ed'
New Auto-Interp
Negative Logits
Mit
-0.70
oret
-0.69
OD
-0.66
orem
-0.66
UE
-0.65
razen
-0.65
iable
-0.62
Gray
-0.62
PNG
-0.59
ues
-0.58
POSITIVE LOGITS
paren
0.89
thro
0.83
fare
0.82
yout
0.79
tsky
0.78
ctic
0.76
bryce
0.75
zan
0.72
ndra
0.71
pine
0.70
Activations Density 0.018%