INDEX

Explanations

punctuation and conjunctions

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

 nuest

-0.19

 follando

-0.14

 pione

-0.13

 novamente

-0.12

 automÃ¡t

-0.10

 cadastr

-0.10

 ragaz

-0.10

 acompanh

-0.10

 siguiente

-0.10

 grÃ¡tis

-0.09

POSITIVE LOGITS

ativ

0.12

 historic

0.11

aÃ§Ãµes

0.11

 reve

0.10

Ãªn

0.10

roup

0.10

 numeric

0.10

iedade

0.10

 mais

0.10

iÃ§Ã£o

0.09

Activations Density 0.092%