INDEX
Explanations
mentions of a specific person named "Bar"
mentions of the name "Bar" in various contexts
New Auto-Interp
Negative Logits
lihood
-0.81
CRIP
-0.72
Dangerous
-0.70
SOS
-0.70
IGHTS
-0.69
IBLE
-0.68
ãģį
-0.68
UAL
-0.67
Instruments
-0.66
uality
-0.64
POSITIVE LOGITS
becue
1.28
riers
1.24
itone
1.21
celona
1.19
rier
1.15
rage
1.05
rington
1.04
bell
1.04
bed
1.04
rie
1.02
Activations Density 0.021%