INDEX

Explanations

words followed by separators

Error and subsequent punctuation

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 ત્યારબાદ

0.45

紝

0.45

 নিচের

0.45

ள்ளதாக

0.44

 असल्याची

0.43

ση

0.43

 Saltar

0.43

 असल्याचे

0.43

 جبکہ

0.42

 जबकि

0.41

POSITIVE LOGITS

2.05

：

1.93

1.42

៖

1.33

_:

1.30

ઃ

1.29

*:

1.27

:...

1.24

：《

1.23

：

1.22

Activations Density 0.961%