INDEX
Explanations
references to characters and legends from Arthurian lore
New Auto-Interp
Negative Logits
Doll
-0.19
Gust
-0.17
785
-0.15
Sto
-0.15
Zac
-0.14
.console
-0.14
Console
-0.14
doll
-0.14
ImageData
-0.14
Han
-0.14
POSITIVE LOGITS
Arthur
0.33
Arthur
0.30
Camel
0.28
knights
0.27
Merlin
0.26
knight
0.24
Knight
0.23
Knights
0.23
Knight
0.22
åĨĨ
0.22
Activations Density 0.056%