INDEX
Explanations
intense expressions of anger or frustration
New Auto-Interp
Negative Logits
EndContext
-0.53
demais
-0.52
trui
-0.50
esModule
-0.50
ModelExpression
-0.50
lour
-0.48
længere
-0.48
BorderRadius
-0.47
sähkö
-0.47
avulla
-0.47
POSITIVE LOGITS
damn
1.83
damned
1.70
fucking
1.64
damn
1.62
Fucking
1.61
goddamn
1.61
fucking
1.59
Damn
1.57
Fucking
1.54
fuckin
1.53
Activations Density 0.185%