INDEX

Explanations

it

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 vannak

-0.64

polate

-0.56

 happen

-0.55

 voltak

-0.55

 deny

-0.55

MessageTagHelper

-0.54

happen

-0.54

 bave

-0.54

 tuta

-0.53

tings

-0.52

POSITIVE LOGITS

is

0.79

 works

0.74

 acts

0.71

’

0.71

all

0.69

 burns

0.68

 functions

0.66

 looks

0.65

 gets

0.65

 cares

0.64

Activations Density 0.010%