INDEX

Explanations

source or other nodes

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

Nested

-0.11

ystack

-0.10

arius

-0.08

ä»

-0.08

allel

-0.08

Viewport

-0.08

arden

-0.08

 sublist

-0.08

nested

-0.08

IPH

-0.08

POSITIVE LOGITS

 node

0.41

 nodes

0.38

èĬĤçĤ¹

0.33

node

0.31

 Node

0.28

_node

0.26

Node

0.26

nodes

0.25

-node

0.24

 Nodes

0.23

Activations Density 0.111%