INDEX
Explanations
proper nouns or specific entities
occurrences of the word "listed" in various contexts
New Auto-Interp
Negative Logits
qua
-0.82
assi
-0.76
co
-0.69
nature
-0.67
ework
-0.66
Phys
-0.65
spir
-0.65
knit
-0.64
sk
-0.64
birth
-0.64
POSITIVE LOGITS
listed
1.12
listing
1.06
listings
0.97
lists
0.84
below
0.79
directories
0.77
above
0.73
MSN
0.72
Lists
0.72
below
0.70
Activations Density 0.010%