INDEX

Explanations

hardware, GPUs, and analytics

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

THING

1.33

не

1.25

âg

1.22

nění

1.21

포츠

1.20

 jeopardize

1.17

тік

1.16

ло

1.13

న్ని

1.13

버스

1.12

POSITIVE LOGITS

est

1.27

राणिक

1.16

 beim

1.13

1.12

ता

1.11

して

1.11

ផ្តល់

1.10

1.09

 implications

1.08

Activations Density 0.000%