INDEX

Explanations

Good followed by context

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

𝚘

2.58

).\

2.50

्रेडिट

2.49

stick

2.37

इये

2.36

cion

2.32

topic

2.29

ल्डेन

2.27

ół

2.27

thread

2.25

POSITIVE LOGITS

еры

3.02

addObject

2.65

藜

2.64

ska

2.63

 سپر

2.62

靼

2.58

لل

2.53

০০

2.48

𝗅

2.44

ྕ

2.43

Activations Density 0.173%