INDEX

Explanations

elasticsearch, python, models, Gradio

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 colouring

1.52

 Coloring

1.45

 coloring

1.45

 dripping

1.37

 photoshop

1.36

 Photoshop

1.34

GameState

1.33

ⓤ

1.28

 Wissenschaft

1.27

 Verpack

1.26

POSITIVE LOGITS

м

1.40

ا

1.27

ه

1.25

л

1.24

lular

1.13

ل

1.10

hase

1.09

に加え

1.07

ым

1.06

oš

1.05

Activations Density 0.000%