INDEX

Explanations

impersonate a style

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

ilden

-0.12

 ridic

-0.09

hib

-0.09

iode

-0.09

owie

-0.09

monkey

-0.09

alloca

-0.08

wan

-0.08

 Ziel

-0.08

 widgets

-0.08

POSITIVE LOGITS

 Sheldon

0.11

 Japanese

0.11

 British

0.10

 stere

0.10

-wise

0.10

Anc

0.10

 ancient

0.10

old

0.09

 manner

0.09

Cyc

0.09

Activations Density 0.266%