INDEX

Explanations

structures

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 buildings

-1.36

 houses

-1.27

 homes

-1.12

 structures

-1.09

houses

-1.02

 dwellings

-1.02

buildings

-0.99

 Structures

-0.97

 Buildings

-0.95

 Houses

-0.92

POSITIVE LOGITS

openzeppelin

0.54

oprot

0.49

 lèvres

0.49

 Polda

0.46

 Révolution

0.45

 vagues

0.45

 larmes

0.45

 quelconque

0.45

#+#

0.44

 compréhension

0.42

Activations Density 0.062%