INDEX

Explanations

card

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

 card

-1.66

 cards

-1.51

 Card

-1.48

 Cards

-1.36

 CARD

-1.33

card

-1.29

Card

-1.29

 CARDS

-1.28

Cards

-1.23

CARD

-1.17

POSITIVE LOGITS

 resourceCulture

0.82

 EconPapers

0.79

+#+#

0.76

 auffi

0.71

 ujednoznacz

0.65

Décès

0.64

Cyfeiriadau

0.63

 myſelf

0.61

 Monfieur

0.61

 Theſe

0.60

Activations Density 0.062%