INDEX

Explanations

describing composition or appearance

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

ጆች

0.38

翹

0.36

LatLng

0.35

 করে

0.35

 அரசின்

0.34

YES

0.34

Knight

0.34

ઘ

0.34

 Karam

0.33

igian

0.33

POSITIVE LOGITS

 berupa

1.40

 consisting

1.16

 consiste

1.14

 consists

1.11

 consist

1.04

 consisted

1.03

是一个

0.97

 består

0.95

 عباره

0.93

 terdiri

0.88

Activations Density 0.136%