INDEX

Explanations

survived

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

kloped

-0.69

Disaster

-0.63

ituary

-0.58

 disaster

-0.57

ⓧ

-0.56

 Disaster

-0.56

 समीक्षाओं

-0.54

Fire

-0.51

 Fire

-0.48

disaster

-0.45

POSITIVE LOGITS

 BoxFit

0.65

 Autorizaciones

0.62

 resourceCulture

0.61

BufferException

0.60

#+#

0.60

 BorderRadius

0.59

 canst

0.58

werd

0.57

ŚĆ

0.56

 bridge

0.55

Activations Density 0.143%