INDEX

Explanations

function followed by parentheses

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

<bos>

-1.34

捩

-1.19

目的是

-1.08

راعة

-1.05

なども

-1.05

と思いました

-1.05

 posizione

-1.04

狨

-1.03

 سایر

-1.03

 RequestMethod

-1.01

POSITIVE LOGITS

()))

1.31

˗

1.18

1.12

()));

1.10

 that

1.09

ⅱ

1.08

())

1.05

–

1.05

Activations Density 0.016%