INDEX

Explanations

a variety of storytelling and warning phrases.

warnings and bad omens

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

FieldNumber

-0.57

 متعلقه

-0.56

ukkah

-0.56

 CanadaChoose

-0.55

 Normdatei

-0.55

ifers

-0.50

 hini

-0.48

xil

-0.48

GenerationType

-0.47

шту

-0.47

POSITIVE LOGITS

 warned

0.84

 warn

0.79

 warnings

0.79

 warning

0.75

 warns

0.71

 يتيمه

0.71

 WARN

0.69

warn

0.64

 Warning

0.62

warnings

0.62

Activations Density 0.715%