INDEX

Explanations

means or channels

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

forName

-0.96

 overall

-0.94

čnosti

-0.94

for

-0.93

ocks

-0.90

ꯀ

-0.88

itig

-0.88

tehen

-0.88

 сторон

-0.88

ências

-0.87

POSITIVE LOGITS

 lens

1.73

 channels

1.72

 medium

1.72

 посред

1.70

 mediums

1.67

 mechanism

1.52

 auspices

1.48

 biais

1.46

 prism

1.38

 means

1.36

Activations Density 0.075%