INDEX

Explanations

pronouns and conjunctions like 'that'

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

end

0.87

cular

0.82

thus

0.80

ಲ್ಲೂ

0.80

ちなみに

0.79

pt

0.77

ق

0.76

ט

0.75

 ಹೀ

0.73

кона

0.73

POSITIVE LOGITS

you

1.32

we

1.32

 there

1.23

 bạn

1.16

 você

1.15

 మీరు

1.13

我们可以

1.11

我們會

1.08

你

1.08

 আমরা

1.06

Activations Density 0.007%