INDEX

Explanations

help me

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

äºĳéĽĨ

-0.09

 ÑĥÐ´Ð¾Ð±

-0.09

edList

-0.09

Kro

-0.08

.groups

-0.08

 Karn

-0.08

èģĶåĲĪä¼ļ

-0.08

vice

-0.08

Ø²ÙĨ

-0.08

è¿¹

-0.08

POSITIVE LOGITS

æĲŀå¥½

0.12

åĬŀå¥½

0.11

åģļä¸Ģä¸ª

0.09

åģļä¸ª

0.09

ä¸Ģéģĵ

0.09

åģļå¥½

0.09

ä¸ĢåĲĮ

0.08

å¥½ä¸įå¥½

0.08

éĵ²

0.08

åĨ³ä¸į

0.08

Activations Density 0.025%