INDEX

Explanations

exclamations with names and topics

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

gee

-0.13

Gee

-0.12

asal

-0.11

-ÑĤÐ¾

-0.10

kes

-0.10

ngu

-0.09

 Banc

-0.09

 hÃ¨

-0.09

POSITIVE LOGITS

how

0.14

 yeah

0.13

yes

0.12

oh

0.12

rana

0.10

 Yeah

0.10

anian

0.10

oho

0.10

saida

0.10

itoris

0.10

Activations Density 0.020%