INDEX

Explanations

class followed by identifier

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

 optimizations

1.30

ا

1.24

 utterances

1.16

ات

1.16

 bookcases

1.15

رد

1.14

ي

1.14

 inclinations

1.13

 impulses

1.13

 axioms

1.12

POSITIVE LOGITS

ing

1.48

↵

1.20

1.16

</h2>

1.09

el

1.07

to

1.02

</blockquote>

0.96

</span>

0.93

the

0.93

0.89

Activations Density 0.000%