INDEX
Explanations
complex emotional relationships and character dynamics in storytelling
New Auto-Interp
Negative Logits
.nc
-0.17
uncture
-0.16
bak
-0.15
.Chain
-0.15
ücken
-0.15
apos
-0.14
cak
-0.14
mite
-0.14
è¹
-0.14
ibble
-0.14
POSITIVE LOGITS
Mad
0.33
Don
0.32
Sterling
0.29
Madison
0.26
Weiner
0.26
Mad
0.25
ÐĶон
0.24
Don
0.24
agency
0.23
Lane
0.23
Activations Density 0.003%