INDEX
Explanations
words and phrases related to emotional states and feelings
New Auto-Interp
Negative Logits
ResourceType
-0.17
annt
-0.15
icom
-0.15
або
-0.15
erk
-0.14
icÃŃ
-0.14
aac
-0.14
affles
-0.14
æĪ¸
-0.14
ermann
-0.14
POSITIVE LOGITS
ron
0.16
acle
0.15
urg
0.15
ronic
0.15
urous
0.14
ronics
0.14
IRECTION
0.14
rons
0.14
114
0.14
balls
0.14
Activations Density 0.008%