INDEX

Explanations

natural language

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

ê¸Ķ

-0.10

gings

-0.09

 nature

-0.09

_prim

-0.09

 inde

-0.09

enschaft

-0.09

 poss

-0.09

bourg

-0.09

orgia

-0.08

POSITIVE LOGITS

istic

0.23

-looking

0.16

istically

0.16

 conversation

0.15

-born

0.13

 language

0.13

 human

0.13

URAL

0.12

-language

0.12

ized

0.12

Activations Density 0.013%