INDEX

Explanations

Dis

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

dis

-1.53

dis

-1.28

Dis

-1.23

Dis

-1.21

DIS

-0.94

DIS

-0.93

 disjoint

-0.82

 disen

-0.81

 displace

-0.75

disc

-0.74

POSITIVE LOGITS

 تانيه

0.86

setVerticalGroup

0.82

NameInMap

0.69

 BoxFit

0.63

 CURL

0.57

 '/':

0.57

 LIABLE

0.56

 للمعارف

0.56

 Тогда

0.55

ViewFeatures

0.54

Activations Density 0.059%