INDEX
Explanations
references to the passage of time
New Auto-Interp
Negative Logits
koa
-0.16
ended
-0.15
Spending
-0.15
aya
-0.15
sov
-0.15
spending
-0.15
за
-0.14
wn
-0.14
è¿«
-0.14
ka
-0.14
POSITIVE LOGITS
ago
0.25
now
0.25
ÑĤепеÑĢÑĮ
0.19
à¤ħब
0.18
longer
0.18
_now
0.17
now
0.17
since
0.17
prior
0.16
Now
0.16
Activations Density 0.043%