INDEX

Explanations

academic publication references

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

but

-1.53

新的

-1.42

 even

-1.29

撓

-1.27

 also

-1.25

rógeno

-1.23

肇

-1.21

🐰

-1.20

 می‌شوند

-1.20

现在的

-1.20

POSITIVE LOGITS

した場合

1.37

 when

1.27

我们需要

1.23

 alcuni

1.20

說道

1.20

 queste

1.18

嚐

1.16

خدمات

1.15

 Эти

1.15

 einigen

1.15

Activations Density 0.053%