INDEX

Explanations

references or mentions of specific technical or scientific concepts, data points, or numerical results

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

fromnode

-0.65

ModelSerializer

-0.64

 Fleury

-0.54

 frappé

-0.54

 Theſe

-0.53

ionych

-0.52

 Pliny

-0.48

jgl

-0.47

 TAMBIÉN

-0.47

 AppBundle

-0.47

POSITIVE LOGITS

Low

1.86

Low

1.67

 Lowe

1.41

LOW

1.05

 Lowell

0.88

 ISNI

0.86

LOW

0.85

 autorytatywna

0.81

 Lowry

0.78

 High

0.73

Activations Density 0.002%