INDEX

Explanations

receptor

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

receptor

-0.81

 Receptor

-0.79

 receptor

-0.79

 Receptors

-0.64

CloseOperation

-0.63

 configureStore

-0.61

 receptors

-0.60

DebuggerNonUser

-0.57

sproz

-0.56

nextProps

-0.53

POSITIVE LOGITS

 betweenstory

0.56

rungsseite

0.55

 panels

0.54

WindowConstants

0.53

homonymie

0.52

 Walkover

0.49

 continúas

0.49

 Stampa

0.48

 sanitario

0.48

 дописавши

0.48

Activations Density 0.025%