INDEX
Explanations
instances of tense shifts and moments of emotional turmoil
New Auto-Interp
Negative Logits
ermo
-0.14
ilon
-0.14
ses
-0.14
ajan
-0.14
iner
-0.14
morgan
-0.14
ypes
-0.13
ofs
-0.13
itti
-0.13
lk
-0.13
POSITIVE LOGITS
others
0.21
Others
0.16
airs
0.16
Others
0.15
others
0.15
words
0.15
Scene
0.14
ัà¸ģà¸Ĺ
0.14
Scene
0.14
scene
0.14
Activations Density 0.428%