INDEX

Explanations

features and characteristics

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

 Operand

-0.09

.strings

-0.09

azar

-0.09

istine

-0.09

FLT

-0.08

 Scripts

-0.08

BIN

-0.08

 Rivers

-0.08

eya

-0.08

Languages

-0.08

POSITIVE LOGITS

 features

0.28

features

0.20

 Features

0.20

 feature

0.19

Features

0.18

_features

0.16

 concepts

0.15

 built

0.15

 operators

0.15

idi

0.15

Activations Density 0.207%