INDEX

Explanations

names, styles, and specific terms

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



-2.81

 ,‬

-2.33

寕

-2.25

﹍﹍

-2.17

なかった

-2.16

 setelah

-2.13

…”

-2.11

 vedea

-2.09

峮

-2.05

 garantis

-2.03

POSITIVE LOGITS

."

2.47

 sebagainya

2.38

 shaker

2.19

茳

1.99

 crean

1.95

"}}>

1.88

 доставка

1.82

 Shaker

1.81

\{

1.80

 idée

1.79

Activations Density 0.003%