INDEX
Explanations
phrases related to the passage of time or duration
references to time durations, particularly in years or months
New Auto-Interp
Negative Logits
eus
-0.68
guyen
-0.68
Redd
-0.66
natureconservancy
-0.60
roth
-0.60
hao
-0.59
inki
-0.59
regon
-0.59
icial
-0.58
rians
-0.58
POSITIVE LOGITS
now
1.31
now
0.91
already
0.85
uninterrupted
0.81
without
0.79
ago
0.78
NOW
0.78
longer
0.77
lately
0.76
Now
0.75
Activations Density 0.120%