INDEX
Explanations
references to a character named "Doc"
references to the name "Doc" in various contexts
New Auto-Interp
Negative Logits
KR
-0.83
KR
-0.81
nings
-0.79
ãĥĦ
-0.69
ande
-0.67
ko
-0.67
bane
-0.66
kar
-0.65
rail
-0.65
sale
-0.64
POSITIVE LOGITS
Doc
4.04
Doc
3.00
doc
2.17
DOC
1.85
docs
1.71
doc
1.61
DOC
1.46
Document
1.37
Marty
1.20
Doct
1.15
Activations Density 0.018%