INDEX

Explanations

2

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

 hereto

-0.63

RenderAtEndOf

-0.61

ंदीखरीदारी

-0.60

۴

-0.58

\{\\

-0.57

الثة

-0.56

forty

-0.55

 صوتيه

-0.55

 vierte

-0.55

POSITIVE LOGITS

0.83

0.82

 Eight

0.76

 eight

0.74

 Eighth

0.71

 eighteenth

0.66

 Eighteen

0.65

 eighteen

0.65

 delapan

0.64

 eighth

0.64

Activations Density 0.005%