INDEX

Explanations

claims of unawareness

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

No Comments

Negative Logits

قایناق‌لار

-0.60

Chham

-0.56

 StatefulWidget

-0.56

Izvori

-0.56

Tja

-0.56

 Brexit

-0.54

Референце

-0.53

Odkazy

-0.52

 poliéster

-0.52

httphttps

-0.52

POSITIVE LOGITS

 awhile

1.97

 unaware

1.30

 oblivious

0.90

 alot

0.82

Alright

0.73

 alright

0.72

 abit

0.71

 Alright

0.70

 parla

0.68

alright

0.66

Activations Density 0.002%