INDEX

Explanations

axis, minus, times, plus

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

 multiplier

-0.10

(--

-0.09

igr

-0.09

ABCDEFGHIJKLMNOP

-0.09

ABCDEFGHI

-0.09

 GENERATED

-0.08

emit

-0.08

_Osc

-0.08

ISOString

-0.08

íĥĢìĿ´

-0.08

POSITIVE LOGITS

 times

0.39

 plus

0.30

times

0.28

 TIMES

0.27

_times

0.23

 vezes

0.23

 Times

0.23

 Ð¿Ð»Ñİ

0.23

 veces

0.21

plus

0.20

Activations Density 0.127%