INDEX
Explanations
the word "today" in various contexts
New Auto-Interp
Negative Logits
recent
-0.18
now
-0.16
ìĿ´ë²Ī
-0.16
ä»Ĭå¹´
-0.16
ionate
-0.16
ses
-0.16
itude
-0.15
ities
-0.15
tonight
-0.15
æľĢè¿ij
-0.15
POSITIVE LOGITS
aday
0.23
lerde
0.21
-day
0.19
jÅ¡ÃŃ
0.18
ÑĪ
0.17
:;↵
0.17
cÃłng
0.16
/new
0.16
arrow
0.16
'hui
0.16
Activations Density 0.044%