INDEX

Explanations

numbers and percentages

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

首先

-1.72

-1.59

虽然

-1.53

自分の

-1.51

на

-1.41

最初

-1.41

 เมื่อ

-1.41

ementara

-1.40

не

-1.38

 Estamos

-1.37

POSITIVE LOGITS

to

2.00

子を

1.47

 kupa

1.47

 seier

1.45

 gamle

1.44

 лесу

1.42

bø

1.41

 яку

1.37

 that

1.35

 annen

1.35

Activations Density 0.159%