INDEX

Explanations

entropy of convex functions

New Auto-Interp

Top Features by Cosine Similarity

Configuration

Prompts (Dashboard)

10,000 prompts, 128 tokens each

Dataset (Dashboard)

lmsys/lmsys-chat-1m

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Leban

-0.10

 asympt

-0.10

uze

-0.09

 invers

-0.09

inverse

-0.09

à¤¹à¤²

-0.09

alian

-0.09

oha

-0.08

-password

-0.08

orgot

-0.08

POSITIVE LOGITS

 conc

0.16

conc

0.16

åĩ

0.15

 upper

0.15

Mon

0.15

 convex

0.14

mon

0.14

 Conc

0.13

-mon

0.13

 increasing

0.12

Activations Density 0.038%