INDEX
Explanations
references to various types of fencing or borders
New Auto-Interp
Negative Logits
leurs
-0.19
phÃŃa
-0.18
undos
-0.18
ires
-0.17
sWith
-0.17
onse
-0.17
itz
-0.16
fate
-0.16
aris
-0.15
fiercely
-0.15
POSITIVE LOGITS
itious
0.21
-forward
0.21
ulous
0.20
gerald
0.20
onacci
0.19
oon
0.19
bruary
0.18
ivals
0.18
amentals
0.18
=f
0.17
Activations Density 0.146%