INDEX
Explanations
references to periods of time, specifically focusing on hours
references to the concept of "hour" and time duration
New Auto-Interp
Negative Logits
LECT
-0.81
ortium
-0.74
liga
-0.68
raviolet
-0.62
ãģį
-0.62
atro
-0.61
founded
-0.61
Bind
-0.60
ce
-0.59
charity
-0.57
POSITIVE LOGITS
glass
1.20
endment
0.98
ILCS
0.87
mins
0.83
Ago
0.80
bnb
0.77
assian
0.76
wise
0.73
neapolis
0.72
utterstock
0.71
Activations Density 0.015%