INDEX

Explanations

embark, embarrass, embellish, imbue, embassy

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

oh

-0.11

yx

-0.10

oi

-0.10

-0.09

ern

-0.09

ergic

-0.09

utton

-0.09

fully

-0.09

bsp

-0.09

OUN

-0.09

POSITIVE LOGITS

emb

0.21

Emb

0.20

emb

0.15

Emb

0.13

assy

0.12

argo

0.11

roid

0.11

ayment

0.10

 embark

0.10

èĥİ

0.10

Activations Density 0.020%