INDEX

Explanations

mourning or lamenting

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

 когда

-2.73

 ก็

-2.58

 если

-2.52

 analyse

-2.45

 очень

-2.30

 arbetar

-2.30

 händer

-2.30

峮

-2.30

 όταν

-2.27

 fulfil

-2.25

POSITIVE LOGITS

𞤢

2.73

枼

2.69

2.55

an

2.53

靣

2.52

,;

2.50

2.48

 blauw

2.47

We

2.42

,”

2.31

Activations Density 0.005%