INDEX

Explanations

dependency to be injected

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

ipel

-0.10

 inher

-0.10

ë°ľ

-0.09

ael

-0.09

_WH

-0.09

å¸ĥ

-0.09

subpackage

-0.09

 Dresden

-0.09

 å¸ĥ

-0.09

POSITIVE LOGITS

DI

0.25

 injection

0.25

 inject

0.25

inject

0.23

 dependency

0.22

 Injection

0.21

 injected

0.21

 injecting

0.21

.Inject

0.21

DI

0.20

Activations Density 0.035%