INDEX

Explanations

filter

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 filter

-0.83

filter

-0.77

 filters

-0.75

 Filter

-0.69

Filter

-0.65

 Filters

-0.59

filters

-0.58

 filtra

-0.51

 filtro

-0.50

 filtros

-0.49

POSITIVE LOGITS

 itſelf

0.78

 Jefus

0.77

SequentialGroup

0.75

 Theſe

0.73

 themſelves

0.69

 utafitiHapana

0.69

脚注の使い方

0.69

 mxArray

0.69

bootstrapcdn

0.68

 becauſe

0.67

Activations Density 0.081%