INDEX

Explanations

sentiment analysis and grouping

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

ubre

-0.09

 Treasure

-0.09

ypo

-0.09

 Hlav

-0.08

 commod

-0.08

iom

-0.08

 verbal

-0.08

OTP

-0.08

iro

-0.08

yped

-0.08

POSITIVE LOGITS

TF

0.16

tf

0.15

 Sent

0.15

Glo

0.14

bag

0.14

bags

0.14

bag

0.13

 sentiment

0.13

 Document

0.13

POS

0.13

Activations Density 0.139%