INDEX

Explanations

names introduced by called

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

and

-1.67

oluble

-1.48

𓐍

-1.34

-1.33

があるので

-1.31

caping

-1.29

や

-1.28

ensitive

-1.27

 problém

-1.27

brtc

-1.25

POSITIVE LOGITS

際に

1.70

 that

1.58

什么事

1.37

 However

1.34

感じが

1.33

 tersenyum

1.33

つづく

1.27

 manteniendo

1.27

 sebelumnya

1.27

ときに

1.25

Activations Density 0.030%