INDEX

Explanations

the word "nearest."

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 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

ervlak

-0.79

ificantly

-0.76

 MediatR

-0.76

 Normdatei

-0.73

 kardashian

-0.73



-0.72

romic

-0.71

 myſelf

-0.70

Lilly

-0.69

 AMOLED

-0.68

POSITIVE LOGITS

nearest

0.99

 nearest

0.88

Nearest

0.88

 Nearest

0.82

 censiti

0.78

 AdapterView

0.69

varrho

0.66

 memer

0.64

ματο

0.63

0.62

Activations Density 0.003%