INDEX
Explanations
temporal markers and references to time
New Auto-Interp
Negative Logits
rack
-0.73
inic
-0.66
natureconservancy
-0.65
urat
-0.64
æ©
-0.64
iour
-0.63
rium
-0.62
inar
-0.62
abama
-0.61
obook
-0.60
POSITIVE LOGITS
however
1.01
there
0.78
though
0.76
there
0.75
moreover
0.71
according
0.68
meanwhile
0.67
Collider
0.67
nobody
0.66
according
0.65
Activations Density 0.073%