INDEX
Explanations
words related to author names
references to the concept of "autumn."
New Auto-Interp
Negative Logits
mary
-0.79
ORK
-0.73
BLE
-0.68
LD
-0.67
IDER
-0.67
earchers
-0.67
nces
-0.66
borough
-0.66
Beir
-0.65
WAY
-0.65
POSITIVE LOGITS
ilus
1.10
onomous
1.03
ogyn
0.96
opsy
0.94
ograph
0.93
ographs
0.93
ographed
0.93
umn
0.92
iful
0.92
emort
0.92
Activations Density 0.010%