INDEX

Explanations

categories followed by examples

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

an

0.47

값을

0.45

其中包括

0.44

into

0.43

 所有

0.42

자의

0.42

연

0.41

 Particularly

0.40

it

0.39

to

0.39

POSITIVE LOGITS

 مثل

1.18

 seperti

1.10

 poput

1.07

 like

1.03

 مانند

1.02

 kuten

0.92

مثل

0.91

เช่น

0.91

 जैसे

0.88

 như

0.86

Activations Density 0.239%