INDEX

Explanations

labels followed by colon

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

呢

0.71

 wiggle

0.63

0.62

 ones

0.58

ونها

0.58

adow

0.57

↵↵

0.57

 حدی

0.57

 whatnot

0.57

getinfo

0.56

POSITIVE LOGITS

 evaluating

1.14

 pelaksanaan

1.13

 depicting

1.12

 assessing

1.12

 examining

1.11

 privind

1.09

 commemorating

1.09

 supplying

1.09

における

1.08

 realizando

1.08

Activations Density 0.313%