INDEX
Explanations
expressions of interpersonal dynamics and dialogue in a dramatic context
New Auto-Interp
Negative Logits
blinked
-0.18
655
-0.15
ilon
-0.15
blinking
-0.15
blink
-0.14
POS
-0.14
Wing
-0.14
363
-0.14
blink
-0.14
screamed
-0.14
POSITIVE LOGITS
kowski
0.17
ÑĤин
0.16
motion
0.16
-motion
0.15
vor
0.14
vang
0.14
akedown
0.14
orian
0.14
bus
0.14
tura
0.14
Activations Density 0.482%