INDEX

Explanations

expressions of worsening situations or outcomes

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

 worst

-1.19

worst

-1.09

 Worst

-0.90

Worst

-0.90

 mergeFrom

-0.78

 Meksiku

-0.70

windowFixed

-0.63

Distribuzione

-0.62

 Walkover

-0.59

市镇

-0.57

POSITIVE LOGITS

 worse

1.23

worse

0.82

 محفوظة

0.61

 Worse

0.61

intern

0.56

__(/*!

0.55

↘

0.53

similar

0.52

 inextrica

0.52

raisemb

0.51

Activations Density 0.002%