INDEX

Explanations

encoding data structures

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ে

1.50

ein

1.45

डिशा

1.35

offic

1.32

יים

1.24

 meniscus

1.17

י

1.16

्

1.15

ticks

1.15

erade

1.14

POSITIVE LOGITS

يل

1.30

ير

1.29

ОВО

1.24

 الاثنين

1.22

सी

1.21

埴

1.18

 répondre

1.17

 raison

1.16

♧

1.15

ствие

1.14

Activations Density 0.001%