INDEX

Explanations

statistics on 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

 numbering

-0.11

 except

-0.11

 totaling

-0.10

except

-0.10

åķ¦

-0.09

Tot

-0.09

amac

-0.09

 especially

-0.08

typings

-0.08

 Twist

-0.08

POSITIVE LOGITS

ãģĨãģ¡

0.18

 alone

0.17

 spread

0.15

alone

0.15

 according

0.13

 Spread

0.13

 split

0.13

ï¼Įåħ¶ä¸Ń

0.12

 distributed

0.12

according

0.12

Activations Density 0.123%