INDEX

Explanations

code comments and structure

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

 Там

-0.82

.~(\

-0.82

Henry

-0.75

 izay

-0.71

udessa

-0.71

Ｉ

-0.71

 there

-0.70

 altın

-0.70

硝

-0.69

 condens

-0.69

POSITIVE LOGITS

 Thirty

0.77

事的

0.76

 Obtain

0.71

كذا

0.69

 अधिक

0.66

っぱり

0.65

 Getty

0.65

 Atmosphäre

0.65

完善

0.65

Obtain

0.64

Activations Density 0.030%