INDEX

Explanations

references to legal violations or misconduct

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

Saharan

-0.66

Kanpo

-0.64

acterial

-0.60

 Pierce

-0.56

neko

-0.54

aerial

-0.52

 Hohen

-0.52

 Numerade

-0.52

 transférez

-0.52

AlterField

-0.51

POSITIVE LOGITS

 malpractice

1.38

 Lipschitz

1.30

 glutathione

1.08

 refugee

0.96

 refugees

0.89

 Refugees

0.75

GSH

0.72

 Glut

0.71

athione

0.69

</thead>

0.65

Activations Density 0.001%