INDEX

Explanations

explaining or describing content

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

SdkError

0.80

/><

0.75

<unused146>

0.74

WhiteElo

0.73

ሖ

0.72

<unused324>

0.72

слав

0.72

<unused1160>

0.72

 htim

0.70

 Når

0.70

POSITIVE LOGITS

 consists

2.19

 contains

2.13

 should

2.05

 would

2.01

 seems

1.99

 could

1.92

 appears

1.91

 belongs

1.88

 does

1.86

 comprises

1.85

Activations Density 0.616%