INDEX
Explanations
emotional expressions and personal reflections in storytelling
New Auto-Interp
Negative Logits
utor
-0.16
ecstatic
-0.15
817
-0.15
åħ
-0.15
thrown
-0.14
uste
-0.14
incoming
-0.14
Incoming
-0.13
upo
-0.13
incoming
-0.13
POSITIVE LOGITS
touched
0.49
touch
0.47
touch
0.43
Touch
0.43
touches
0.42
TOUCH
0.42
touching
0.40
-touch
0.38
Touch
0.38
_touch
0.34
Activations Density 0.165%