INDEX

Explanations

high-dimensional

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

vig

-0.09

 Ordered

-0.09

 overst

-0.09

_cmos

-0.09

æĨ

-0.09

 Huffman

-0.09

 omnip

-0.09

ä¿

-0.09

anh

-0.09

egasus

-0.08

POSITIVE LOGITS

 dimension

0.41

 dimensions

0.33

 Dimension

0.32

dimension

0.31

Dimension

0.28

 Dimensions

0.27

-dimensional

0.25

 dimensional

0.25

dimensions

0.25

Dimensions

0.24

Activations Density 0.052%