INDEX
Explanations
phrases indicating urgency or immediacy
New Auto-Interp
Negative Logits
finally
-0.25
finally
-0.19
Finally
-0.19
Finally
-0.18
recently
-0.18
eventually
-0.17
ultimately
-0.17
recent
-0.17
Recently
-0.17
Recently
-0.16
POSITIVE LOGITS
already
0.21
Already
0.20
immediately
0.19
Already
0.18
already
0.17
sofort
0.17
Immediately
0.16
chóng
0.15
Pearce
0.15
began
0.15
Activations Density 0.161%