INDEX
Explanations
mentions of computer-related terms or actions
occurrences of the term "computer."
New Auto-Interp
Negative Logits
agy
-0.74
idas
-0.74
ikk
-0.69
alties
-0.69
[&
-0.67
Tuls
-0.67
Æ
-0.67
govtrack
-0.66
Roose
-0.65
Mour
-0.64
POSITIVE LOGITS
computer
3.44
computers
2.89
computer
2.67
Computer
2.56
Computer
2.48
computing
1.89
laptop
1.89
Comput
1.82
puter
1.64
machine
1.64
Activations Density 0.013%