INDEX

Explanations

also followed by evaluation or attribute

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

1.18

1.16

<bos>

1.14

nya

1.06

st

1.04

def

1.03

plaintext

1.02

هم

0.99

carbox

0.96

ness

0.94

POSITIVE LOGITS

 እንዲሁ

1.65

 הת

1.42

らった

1.41

らえる

1.37

वायु

1.37

 კი

1.36

ষুধ

1.34

 සමඟ

1.34

 ஆவார்

1.32

 нема

1.28

Activations Density 0.077%