INDEX

Explanations

people identified by nationality/ethnicity

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

에

1.81

،

1.74

О

1.69

，

1.59

 своего

1.58

1.54

 имя

1.52

ン

1.52

}$

1.51

 жены

1.49

POSITIVE LOGITS

ों

1.52

 Rupees

1.52

য়ের

1.48

 stagnant

1.48

propri

1.38

了一种

1.34

 pesticides

1.33

 expats

1.31

ят

1.30

 superconduct

1.30

Activations Density 0.049%