INDEX

Explanations

too [adjective] constructions

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

 enough

-0.15

 Enough

-0.11

bel

-0.10

 Äĳá»§

-0.10

eyer

-0.10

afa

-0.10

-sized

-0.10

 ãĤĿ

-0.09

 Germ

-0.09

ä¸įäºĨ

-0.09

POSITIVE LOGITS

-too

0.14

Too

0.13

Too

0.13

too

0.12

 Äĳá»ĥ

0.12

 å¤ª

0.12

/to

0.11

assy

0.11

 demasi

0.11

å¤ª

0.11

Activations Density 0.043%