INDEX
Explanations
references to locations or spatial contexts in narratives
New Auto-Interp
Negative Logits
orb
-0.17
ORS
-0.16
ORIA
-0.16
Ctx
-0.16
oria
-0.15
ORB
-0.15
orian
-0.15
ailable
-0.15
İ
-0.15
modal
-0.15
POSITIVE LOGITS
ebo
0.20
Cand
0.16
uke
0.16
uby
0.16
logo
0.15
MSNBC
0.15
inue
0.14
bindings
0.14
acro
0.14
bast
0.14
Activations Density 0.034%