INDEX

Explanations

numbers and code

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CIT

-0.24

growth

-0.23

incoming

-0.23

fax

-0.23

çĦ¦

-0.22

Lug

-0.22

è¶¾

-0.22

ç³

-0.22

ä¸Ģä¼ļ

-0.21

æĥ®

-0.21

POSITIVE LOGITS

kiem

0.23

ħ§

0.22

 erupt

0.21

ç¥Ń

0.21

å¤©èĬ±

0.21

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

0.21

iful

0.20

 setup

0.20

eee

0.20

 supervise

0.20

Activations Density 0.054%