INDEX
Explanations
numerical references, particularly years
New Auto-Interp
Negative Logits
ïľ
-0.18
/cop
-0.17
üme
-0.17
озв
-0.16
men
-0.16
iom
-0.16
566
-0.16
Men
-0.15
xBB
-0.15
zÅij
-0.14
POSITIVE LOGITS
APR
0.20
ëĦ·
0.19
484
0.19
423
0.18
400
0.18
apr
0.18
fou
0.18
apr
0.18
402
0.17
.iv
0.17
Activations Density 0.119%