INDEX

Explanations

code snippets and technical discussions

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

几次

-1.01

 accus

-0.90

our

-0.86

rouw

-0.85

 Polyester

-0.83

 entsprechend

-0.82

onav

-0.82

 столько

-0.82

LOC

-0.79

젼

-0.79

POSITIVE LOGITS

einem

0.94

Modell

0.94

 mewujudkan

0.93

waża

0.92

knew

0.91

 exists

0.90

 woes

0.87

 cán

0.85

 actief

0.85

 قه

0.84

Activations Density 0.045%