INDEX

Explanations

descriptor followed by a noun

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 กลุ่ม

1.63

 Bộ

1.61

 함수의

1.60

독

1.58

 ใน

1.58

 功能

1.58

 нова

1.57

 Horizontal

1.57

 Же

1.55

 국내

1.55

POSITIVE LOGITS

 morti

1.59

 odio

1.52

it

1.51

 merda

1.49

 magari

1.47

 fucking

1.45

 smell

1.43

 recuerdo

1.39

 cramps

1.38

 tudo

1.38

Activations Density 1.712%