INDEX

Explanations

numbers inside parentheses

Academic papers

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

 unknownFields

-0.78

Portale

-0.63

 GenerationType

-0.63

addGap

-0.62

ANTLR

-0.59

 BorderRadius

-0.59

WebControls

-0.58

FontOfSize

-0.56

 الرخصة

-0.55

piecze

-0.54

POSITIVE LOGITS

 Anſ

0.60

Efq

0.59

 Majefty

0.56

 fubject

0.54

 ſeveral

0.52

duate

0.51

 Diſ

0.50

 Theſe

0.50

nass

0.50

()")

0.50

Activations Density 0.747%