INDEX
Explanations
actions involving rubbing or physical contact
New Auto-Interp
Negative Logits
SpringBootTest
-0.78
SpringRunner
-0.68
Verantwortung
-0.57
DOCTYPE
-0.57
kasarigan
-0.55
primaryStage
-0.54
theatre
-0.53
UKU
-0.53
theatre
-0.52
theater
-0.52
POSITIVE LOGITS
rubbing
1.42
rubs
1.38
rubbed
1.33
rub
1.19
frot
1.14
grinding
1.10
Grinding
1.07
grind
1.05
scraping
1.01
scrape
0.99
Activations Density 0.201%