INDEX

Explanations

said people

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

lope

-0.09

Specifier

-0.08

_OW

-0.08

exh

-0.08

 uÄŁ

-0.08

Ã¡r

-0.08

hei

-0.08

 preval

-0.07

oxy

-0.07

Registrar

-0.07

POSITIVE LOGITS

 spokesperson

0.22

 spokesman

0.21

 spokes

0.21

 said

0.19

 spokeswoman

0.16

 speaking

0.15

 spoke

0.13

 interviewed

0.13

said

0.12

 added

0.12

Activations Density 0.097%