INDEX

Explanations

information requests and descriptions

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

一段时间

-1.70

糴

-1.65

おはよう

-1.58

呲

-1.53

 avem

-1.49

一張

-1.48

 cuno

-1.47

៍

-1.45

 чрезвы

-1.45

 prêtre

-1.44

POSITIVE LOGITS

 will

1.73

 даже

1.73

或是

1.66

1.64

or

1.64

 после

1.63

 work

1.55

 или

1.54

1.51

↵↵↵

1.49

Activations Density 0.816%