INDEX

Explanations

arguing and conflict

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

¶Į

-0.10

adow

-0.10

iple

-0.09

plib

-0.09

velte

-0.09

uve

-0.09

/pl

-0.09

andles

-0.09

utter

-0.09

QA

-0.09

POSITIVE LOGITS

 argument

0.23

 Argument

0.21

 arguments

0.20

argument

0.19

 argue

0.18

Argument

0.18

arguments

0.18

Arguments

0.18

 argued

0.18

 arguing

0.17

Activations Density 0.081%