INDEX
Explanations
terms related to time and historical events
phrases indicating time references or periods
New Auto-Interp
Negative Logits
"},{"-0.78
"}],"
-0.75
..."
-0.75
)))
-0.74
))))
-0.74
]}
-0.69
yles
-0.68
Lastly
-0.67
)",
-0.66
ascus
-0.66
POSITIVE LOGITS
starters
0.73
fact
0.70
verning
0.66
sofar
0.65
Consider
0.64
Sure
0.62
ensibly
0.62
industrialized
0.59
irteen
0.58
ccording
0.57
Activations Density 0.545%