INDEX

Explanations

phrases indicating disbelief or impossibility

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 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

 diretto

-0.60

 kveld

-0.46

 buone

-0.46

 seules

-0.45

 colère

-0.44

 Safer

-0.44

 legging

-0.44

 Kitty

-0.43

 skolan

-0.43

 dernières

-0.43

POSITIVE LOGITS

+#+#

1.04

RectangleBorder

0.85

extAlignment

0.84

 Roskov

0.76



0.70

 مشين

0.69

PreferredItem

0.66

 surla

0.64

 архивлан

0.64

twimg

0.63

Activations Density 0.115%