INDEX

Explanations

Tw

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

are

-1.05

can

-0.77

-0.63

 насеље

-0.60

 were

-0.60

 will

-0.59

are

-0.58

get

-0.57

 gave

-0.56

 talked

-0.55

POSITIVE LOGITS

 utafitiHapana

0.73

PerformLayout

0.60

 defStyle

0.60

tvguidetime

0.59

 kasarigan

0.59

 Majefty

0.56

AndEndTag

0.55

 eventName

0.54

 neceff

0.54

سطس

0.53

Activations Density 0.000%