INDEX
Explanations
references to academic publications and medical terminology related to medications and diseases
New Auto-Interp
Negative Logits
itſelf
-0.72
Chriſt
-0.71
themſelves
-0.69
houſe
-0.67
ſeveral
-0.67
Jefus
-0.66
myſelf
-0.65
stiefel
-0.64
againſt
-0.63
himſelf
-0.62
POSITIVE LOGITS
NameInMap
0.88
flu
0.79
flu
0.73
Flu
0.72
Flu
0.70
FLT
0.70
Prisoners
0.68
InjectAttribute
0.67
capture
0.67
Wicidata
0.66
Activations Density 2.920%