INDEX
Explanations
references to the concept of time
New Auto-Interp
Negative Logits
stadt
-0.18
ruz
-0.16
oyer
-0.16
aby
-0.15
rador
-0.15
XHR
-0.15
ostat
-0.14
uzzy
-0.14
terra
-0.14
udded
-0.14
POSITIVE LOGITS
travel
0.25
capsule
0.24
machine
0.23
Machine
0.23
bomb
0.22
_travel
0.22
capsules
0.22
pieces
0.22
Machine
0.22
traveling
0.22
Activations Density 0.041%