INDEX
Explanations
expressions of subjective emotional experiences
New Auto-Interp
Negative Logits
ſche
-0.66
houſe
-0.64
ſelf
-0.59
deſt
-0.57
AddTagHelper
-0.57
igate
-0.56
ſta
-0.55
xtext
-0.54
nezeu
-0.54
newBuilder
-0.54
POSITIVE LOGITS
feel
1.61
Feel
1.55
Feel
1.52
felt
1.46
feeling
1.45
FEEL
1.45
feel
1.42
feels
1.41
Feeling
1.34
Feeling
1.30
Activations Density 0.061%