INDEX
Explanations
actions associated with movement and progression
New Auto-Interp
Negative Logits
erie
-0.17
upward
-0.17
orer
-0.16
elop
-0.15
dzi
-0.15
downward
-0.14
apel
-0.14
.setUp
-0.14
stasy
-0.14
Ep
-0.14
POSITIVE LOGITS
across
0.32
Across
0.28
Across
0.27
toward
0.24
along
0.24
towards
0.23
Along
0.20
past
0.20
along
0.20
Along
0.19
Activations Density 0.214%