INDEX

Explanations

squared math expressions

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

 scre

-0.11

Anywhere

-0.10

 Braun

-0.10

(*)

-0.09

 Fritz

-0.09

 tide

-0.09

 Bened

-0.09

çĪ½

-0.09

 Pole

-0.09

 Sylv

-0.09

POSITIVE LOGITS

)^

0.23

 square

0.17

 squared

0.17

]^

0.14

 squares

0.13

.square

0.13

Squared

0.13

_square

0.13

 ÙħØ±Ø¨Ø¹

0.13

 Square

0.13

Activations Density 0.041%