INDEX

Explanations

technical and formal writing

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 advanced

-0.84

advanced

-0.78

 presented

-0.76

forChild

-0.76

 offered

-0.75

presented

-0.75

offered

-0.71

put

-0.71

 raised

-0.69

Put

-0.69

POSITIVE LOGITS

 fixed

0.52

ReadInt

0.51

riage

0.46

me

0.46

fixed

0.43

 fixing

0.43

 CreateTagHelper

0.43

 comigo

0.42

 Fixed

0.42

 povezave

0.42

Activations Density 0.001%