INDEX

Explanations

references to a specific researcher in a scientific context

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

Personensuche

-0.79

 BoxDecoration

-0.75

 DBNull

-0.69

featureID

-0.64

 ProtoMessage

-0.64

]-->

-0.62

 decathlon

-0.61

 simb

-0.59

 pères

-0.59

 StringField

-0.57

POSITIVE LOGITS

 Hamilton

2.55

Hamilton

2.31

 HAMILTON

2.03

hamilton

1.40

 hamilton

1.38

AMILTON

1.23

ransition

0.55

 Burnet

0.49

 estekak

0.48

 relâche

0.48

Activations Density 0.000%