INDEX

Explanations

feature selection

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 feature

-1.09

 features

-1.09

FEATURES

-0.88

features

-0.84

 Features

-0.76

ABB

-0.76

Feature

-0.73

rollable

-0.73

зможно

-0.73

íts

-0.72

POSITIVE LOGITS

 extraction

1.30

 extractor

1.09

 vector

1.05

 engineering

1.05

 space

1.02

 selection

1.00

 vectors

0.96

vector

0.94

Extraction

0.93

 Space

0.92

Activations Density 0.022%