INDEX
Explanations
locations and positions in a narrative context
New Auto-Interp
Negative Logits
opi
-0.16
ibase
-0.15
oven
-0.15
-0.15
tunnels
-0.15
ighton
-0.14
rift
-0.14
klu
-0.14
ocket
-0.13
atti
-0.13
POSITIVE LOGITS
platform
0.29
platforms
0.28
bench
0.27
platform
0.26
steps
0.26
stool
0.25
PLATFORM
0.23
balcony
0.23
Platform
0.22
plataforma
0.22
Activations Density 0.193%