INDEX
Explanations
references to individuals, particularly focusing on their experiences and emotional states
New Auto-Interp
Negative Logits
aber
-0.21
tk
-0.20
ink
-0.16
inker
-0.15
ted
-0.15
ingly
-0.14
ÚĨÙĩ
-0.14
byss
-0.14
ове
-0.14
tm
-0.14
POSITIVE LOGITS
/entity
0.18
/people
0.17
nels
0.17
hood
0.17
nage
0.16
nel
0.16
/company
0.16
/entities
0.15
ģına
0.14
acle
0.14
Activations Density 0.035%