INDEX
Explanations
references to machines or machine-related terms
references to "machine" in various contexts
New Auto-Interp
Negative Logits
raints
-0.92
alez
-0.82
ificant
-0.81
acious
-0.80
orship
-0.79
uating
-0.79
ibilities
-0.77
omes
-0.75
uates
-0.74
iaries
-0.74
POSITIVE LOGITS
gun
0.93
guns
0.90
machines
0.79
Machine
0.76
machine
0.73
guns
0.73
gunned
0.71
learning
0.71
Robo
0.70
Learning
0.70
Activations Density 0.021%