INDEX

Explanations

the string "Ber"

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

-0.86

 Weir

-0.75

shape

-0.69

 Paula

-0.69

Pud

-0.68

 Laval

-0.68

isLogin

-0.68

zwe

-0.68

 تانيه

-0.68

uesday

-0.67

POSITIVE LOGITS

Ber

1.58

 Berk

1.52

Ber

1.42

BER

1.33

 Berman

1.26

 Bertie

1.25

 beret

1.19

 Bergh

1.16

 Bergman

1.14

 Berg

1.13

Activations Density 0.033%