INDEX
Explanations
words related to excitement or exhilarating experiences
New Auto-Interp
Negative Logits
omon
-0.17
ffect
-0.15
ontology
-0.14
Guil
-0.14
owing
-0.14
Berry
-0.14
во
-0.13
Substance
-0.13
ök
-0.13
Dar
-0.13
POSITIVE LOGITS
ursions
0.27
ursion
0.23
els
0.21
iting
0.21
ise
0.21
urs
0.20
elsius
0.20
ited
0.20
ision
0.20
ite
0.19
Activations Density 0.008%