INDEX

Explanations

specific topics and entities

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 явно

-2.41

เขา

-2.34

 nyeri

-2.22

皺

-2.22

擄

-2.17

くに

-2.16

 не

-2.13

憂

-2.03

 Entire

-2.00

必須

-1.99

POSITIVE LOGITS

眥

2.94

 Houſe

2.75

튿

2.59

2.58

••

2.56

甚至是

2.55

 veröffentlicht

2.53

 uſed

2.52

 essas

2.47

 które

2.41

Activations Density 0.003%