INDEX
Explanations
references to historical or nostalgic experiences and themes related to time
New Auto-Interp
Negative Logits
adow
-0.15
à¹Ĩ
-0.15
±
-0.14
terminator
-0.14
getti
-0.14
icolon
-0.13
ulin
-0.13
idences
-0.13
itations
-0.13
å¤ķ
-0.13
POSITIVE LOGITS
retro
0.38
backward
0.38
åĽŀ
0.37
back
0.35
backwards
0.34
transported
0.32
Retro
0.32
åĽŀ
0.32
transport
0.32
flashback
0.30
Activations Density 0.083%