INDEX

Explanations

material followed by descriptor

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

 pembun

-2.91

刂

-2.88

都是

-2.77

}$

-2.59

 aloof

-2.55

镦

-2.50

 boneka

-2.50

 стал

-2.36

🍥

-2.36

 категории

-2.30

POSITIVE LOGITS

弍

3.30

 vollständ

3.19

ization

3.14

⚋

2.73

</h4>

2.69

ześnie

2.63

行きます

2.63

とはいえ

2.61

⟞

2.59

鉝

2.59

Activations Density 0.024%