INDEX

Explanations

mathematical notations and code formatting

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

 inmediata

1.27

 pleinement

1.27

 somewhat

1.25

 एक्चुअली

1.22

檄

1.22

Escolh

1.21

幾乎

1.20

ことがあります

1.19

ಜ್ಯ

1.19

ANCEL

1.16

POSITIVE LOGITS

1.23

1.11

1.08

 الك

1.04

mun

1.03

atas

1.01

ize

1.01

 Heck

1.01

1.00

Activations Density 0.001%