INDEX
Explanations
references to specific time durations and quantities, often in a structured context
New Auto-Interp
Negative Logits
opleft
-0.18
yen
-0.15
sey
-0.14
regunta
-0.14
bah
-0.14
795
-0.14
در
-0.13
avier
-0.13
.twimg
-0.13
figcaption
-0.13
POSITIVE LOGITS
ago
0.27
interval
0.21
span
0.20
ago
0.20
nữa
0.20
Ago
0.20
назад
0.20
-old
0.18
passed
0.18
validity
0.16
Activations Density 0.109%