INDEX

Explanations

word or phrase

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

 vaccination

-0.10

ãģ°ãģĭãĤĬ

-0.09

kip

-0.09

ophilia

-0.08

æĮģãģ¡

-0.08

atrice

-0.08

oller

-0.08

 bidding

-0.08

.openg

-0.08

 Knox

-0.08

POSITIVE LOGITS

 creation

0.36

creation

0.28

use

0.26

 establishment

0.23

 receipt

0.22

 removal

0.22

 formation

0.22

Creation

0.20

 Creation

0.20

 introduction

0.19

Activations Density 0.221%