INDEX

Explanations

also known as

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

が

-0.88

 gerçekten

-0.87

 которые

-0.87

という感じ

-0.86

によって

-0.86

 ситуа

-0.86

 terutama

-0.85

ということです

-0.85

というのは

-0.84

については

-0.84

POSITIVE LOGITS

 known

5.91

known

4.13

Known

3.61

 called

3.61

 Known

3.34

 referred

3.22

 conocido

3.06

 conhecido

2.88

 conocida

2.64

 извест

2.63

Activations Density 0.122%