INDEX
Explanations
dates mentioned in context
years and significant dates within the text
New Auto-Interp
Negative Logits
Reloaded
-0.63
amins
-0.59
plur
-0.58
verbs
-0.58
superflu
-0.58
manifold
-0.56
offs
-0.55
fam
-0.54
categ
-0.53
izations
-0.53
POSITIVE LOGITS
isSpecialOrderable
0.72
lez
0.69
displayText
0.67
.,
0.66
burgh
0.65
â̲
0.64
Became
0.63
Miko
0.63
JD
0.61
ramid
0.60
Activations Density 0.082%