INDEX

Explanations

strategy or technique description

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

ibase

-0.10

hoa

-0.10

acha

-0.10

 inversion

-0.09

 Ð·Ð°Ð²Ð¸ÑģÐ¸Ð¼

-0.09

 modelo

-0.08

Jew

-0.08

irket

-0.08

POSITIVE LOGITS

 technique

0.20

 techniques

0.18

 strategy

0.16

 strategies

0.16

 Technique

0.15

 Techniques

0.15

 proven

0.13

çŃĸ

0.12

 Strategy

0.12

 Strategies

0.12

Activations Density 0.120%