INDEX
Explanations
references to individuals' roles and contributions within a narrative context
New Auto-Interp
Negative Logits
avit
-0.15
çĿĽ
-0.14
outil
-0.14
emet
-0.14
eil
-0.14
íĦ´
-0.14
erin
-0.14
ucz
-0.14
ÑĥÑĩа
-0.13
ì°©
-0.13
POSITIVE LOGITS
kas
0.17
enido
0.16
asmus
0.15
ghi
0.15
faces
0.14
ıza
0.14
å®®
0.14
141
0.14
czy
0.14
heir
0.14
Activations Density 0.200%