INDEX

Explanations

seemingly random sequences of adjacent numbers

ISBN-like patterns

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

 onCancelled

-0.59

 vidare

-0.56

 colorés

-0.54

 détru

-0.54

 fermés

-0.54

 conflits

-0.51

 larmes

-0.50

 étrang

-0.50

pośred

-0.50

 souffrance

-0.50

POSITIVE LOGITS

 kasarigan

0.92

rungsseite

0.73

 <<<<<<<<<<<<<<

0.71

UnsafeEnabled

0.64

 pinulongan

0.64

DockStyle

0.62

 himo

0.59

RegressionTest

0.59

IonicModule

0.56

neurial

0.55

Activations Density 0.224%