INDEX
Explanations
references to historical figures and events, particularly in the context of English medieval history
New Auto-Interp
Negative Logits
ìĹĩ
-0.15
abra
-0.15
ystone
-0.14
ToProps
-0.14
Ģ
-0.14
nton
-0.14
.dds
-0.14
ahy
-0.14
tı
-0.14
#__
-0.14
POSITIVE LOGITS
128
0.24
129
0.23
133
0.22
134
0.22
130
0.22
crus
0.22
132
0.21
123
0.21
131
0.21
135
0.20
Activations Density 0.030%