INDEX

Explanations

the answer to everything

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

ottom

-0.10

 doll

-0.10

 dolls

-0.09

 Brendan

-0.09

WithPath

-0.09

ahoma

-0.09

reet

-0.09

 dock

-0.09

 Hudson

-0.08

OTS

-0.08

POSITIVE LOGITS

 Hitch

0.23

 hitch

0.22

Vog

0.17

 Douglas

0.15

 towel

0.14

BBC

0.12

 Guide

0.12

 gall

0.11

Dou

0.11

Tow

0.11

Activations Density 0.026%