INDEX
Explanations
references to biblical texts and their citations
New Auto-Interp
Negative Logits
160
-0.18
360
-0.17
204
-0.17
80
-0.17
onz
-0.17
206
-0.17
66
-0.17
162
-0.16
76
-0.16
100
-0.15
POSITIVE LOGITS
ollen
0.15
à¹Ĥย
0.14
lok
0.14
THR
0.14
orch
0.14
ervas
0.13
ÑĢеÑĪ
0.13
ãĤ¦ãĥĪ
0.13
Centers
0.13
lek
0.13
Activations Density 0.209%