INDEX

Explanations

in the corner

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

abyrin

-0.10

 ngÃ´i

-0.10

neighbor

-0.09

_MR

-0.09

 surround

-0.09

Miz

-0.09

_LR

-0.08

 Inside

-0.08

hausen

-0.08

Ø³ÙĪØ¨

-0.08

POSITIVE LOGITS

 corner

0.38

 corners

0.28

corner

0.28

 Corner

0.27

Corner

0.26

-corner

0.21

 comer

0.18

 kÃ¶ÅŁ

0.17

_corner

0.17

 nearby

0.16

Activations Density 0.041%