INDEX

Explanations

section headers and dates

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

</h2>

-1.64

nehmen

-1.38

 REMEMBER

-1.36

 休闲

-1.35

TAINMENT

-1.34

même

-1.30

 Litu

-1.30

 всѣ

-1.28

 нѣ

-1.26

我们的

-1.25

POSITIVE LOGITS

 when

2.02

or

1.94

for

1.88

 that

1.87

at

1.65

 there

1.55

 another

1.48

1.39

 like

1.37

any

1.34

Activations Density 0.428%