INDEX

Explanations

absorb

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

 تانيه

-0.60

 salido

-0.52

vänd

-0.49

 REPORT

-0.48

 társ

-0.46

httphttps

-0.46

unanje

-0.45

led

-0.44

 scattata

-0.44

 وتسجيلات

-0.44

POSITIVE LOGITS

EDEFAULT

0.76

انيف

0.65

delwed

0.64

vician

0.60

 cock

0.58

richlet

0.58

 BIBSYS

0.57

Composable

0.56

المناصب

0.55

AsStream

0.54

Activations Density 0.054%