INDEX

Explanations

running a node using a tool

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

 tokenize

-0.10

 tokens

-0.10

ozem

-0.10

lops

-0.10

 Crypto

-0.09

 Crypt

-0.09

 token

-0.09

 Tokens

-0.09

 Huffman

-0.09

inth

-0.09

POSITIVE LOGITS

 Tender

0.16

 mast

0.15

 consensus

0.14

 Elect

0.14

 gossip

0.14

 node

0.14

 nodes

0.14

 peers

0.13

 elect

0.13

èĬĤçĤ¹

0.13

Activations Density 0.026%