INDEX

Explanations

reading

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

 saites

-0.98

uxxxx

-0.96

 tartalomajánló

-0.83

 BoxFit

-0.82

 nahilalakip

-0.75

 Owned

-0.74

 transfieras

-0.74

DockStyle

-0.72

 autorytatywna

-0.72

 المعيارى

-0.71

POSITIVE LOGITS

take

0.46

 take

0.46

Take

0.40

endar

0.39

testcase

0.38

verwijspagina

0.38

pö

0.36

 taken

0.35

 patrio

0.35

ragma

0.35

Activations Density 0.017%