INDEX

Explanations

smoking or experiments

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

itant

-0.51

 Meksiku

-0.51

 Roskov

-0.50

smoke

-0.50

 onCancelled

-0.49

Enfant

-0.46

sule

-0.45

AccessorTable

-0.44

 ViewHolder

-0.44

consulté

-0.44

POSITIVE LOGITS

PreferredItem

0.88

يكب

0.62

rungsseite

0.59

 ddelweddau

0.57

ContentAsync

0.57

ModelAdmin

0.57

<bos>

0.56

 Reverso

0.54



0.54

Activations Density 0.007%