INDEX

Explanations

code blocks with non-English words

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

as

1.52

are

1.37

at

1.32

1.29

ms

1.24

can

1.20

it

1.15

1.12

AT

1.09

ana

1.06

POSITIVE LOGITS

ي

1.01

но

0.92

 দ্য

0.91

 просты

0.91

 поги

0.90

 који

0.88

});

0.88

 centrales

0.88

 молоды

0.87

 determinadas

0.87

Activations Density 0.001%