INDEX

Explanations

data preprocessing and filtering

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

写法

0.38

 reprodu

0.38

 воспроиз

0.38

开头

0.38

报告

0.37

 satın

0.37

धर

0.36

维持

0.36

ന്ത്യ

0.36

 recrut

0.36

POSITIVE LOGITS

 preprocessing

0.93

 filtering

0.91

 undergo

0.85

 undergoes

0.85

 undergone

0.82

Filtering

0.81

 underwent

0.80

Preprocessing

0.80

filtering

0.80

 purification

0.79

Activations Density 0.110%