INDEX
Explanations
references to specific targets or entities in the text
New Auto-Interp
Negative Logits
dysplasia
-0.70
CBA
-0.68
xffffff
-0.67
fistula
-0.66
Jaz
-0.66
CBA
-0.65
colitis
-0.63
httphttps
-0.61
writing
-0.60
gustó
-0.59
POSITIVE LOGITS
targets
1.83
target
1.73
TARGET
1.70
Target
1.69
Targets
1.63
TARGET
1.61
target
1.54
Target
1.54
targets
1.53
cible
1.45
Activations Density 0.083%