INDEX
Explanations
words related to feelings of heaviness or burden
terms related to the concepts of boundlessness or unhappiness
New Auto-Interp
Negative Logits
anwhile
-0.86
Nanto
-0.81
Carbuncle
-0.81
cair
-0.78
tsky
-0.76
enegger
-0.73
å§«
-0.73
fman
-0.72
uyomi
-0.72
Mata
-0.69
POSITIVE LOGITS
rep
0.97
ishable
0.90
assuming
0.89
rave
0.78
unp
0.78
anging
0.77
ashed
0.76
itt
0.76
irable
0.75
orter
0.75
Activations Density 0.016%