INDEX

Explanations

the word "that"

that

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

Negative Logits

 jenes

-0.71

 THAT

-0.65

 jenem

-0.64

erker

-0.60

 jenen

-0.59

那种

-0.57

omio

-0.57

Personensuche

-0.56

 jener

-0.55

 daarvan

-0.54

POSITIVE LOGITS

<bos>

1.10

 cherchés

0.62

0.60

ContentAsync

0.53

 beginnetje

0.52

RegistryLite

0.51

",

0.50

".

0.49

Activations Density 0.281%