INDEX

Explanations

string matching

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

번호

-0.79

üyü

-0.71

思います

-0.71

 drafted

-0.70

 prev

-0.69

grouped

-0.69

 unsatisfied

-0.69

 agrup

-0.69

 Breach

-0.69

 preceding

-0.68

POSITIVE LOGITS

 matching

1.30

matched

1.28

Matched

1.22

Matching

1.20

匹配

1.19

 shorter

1.17

 Matching

1.17

 match

1.17

 matches

1.13

 matched

1.10

Activations Density 0.028%