INDEX
Explanations
phrases related to significant changes over time
phrases indicating significant changes or progress over time
New Auto-Interp
Negative Logits
))))
-0.73
}}}
-0.68
raid
-0.64
usra
-0.63
ometimes
-0.62
tumblr
-0.62
});
-0.60
oops
-0.58
NX
-0.58
inki
-0.58
POSITIVE LOGITS
since
1.57
lately
1.43
since
1.28
recently
1.11
over
1.04
Since
0.96
Since
0.93
thus
0.87
historically
0.85
recent
0.80
Activations Density 0.503%