INDEX

Explanations

increasingly popular

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

ordin

-0.09

 Dodd

-0.09

 CURRENT

-0.08

suy

-0.08

uri

-0.08

uji

-0.08

ï¾Ł

-0.08

bett

-0.08

atoon

-0.08

 current

-0.08

POSITIVE LOGITS

 increasingly

0.21

 thanks

0.14

 across

0.13

è¶Ĭ

0.12

 Previously

0.12

Previously

0.12

 unprecedented

0.11

 previously

0.11

 mainstream

0.11

thanks

0.11

Activations Density 0.106%