INDEX

Explanations

clauses describing capabilities or content

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

omers

-0.12

uding

-0.10

 serm

-0.09

omer

-0.09

overs

-0.08

urons

-0.08

nir

-0.08

 Brock

-0.08

alth

-0.08

POSITIVE LOGITS

 already

0.14

already

0.12

 support

0.12

 Already

0.11

ched

0.10

FML

0.10

INLINE

0.09

 suits

0.09

 suit

0.09

Already

0.09

Activations Density 0.081%