INDEX

Explanations

parenthesized abbreviations

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

Здесь

-2.28



-2.28

inação

-2.16

というわけで

-2.13

-”

-2.08

Probably

-2.08

Благодаря

-2.08

᪥

-2.05

悝

-2.03

 Kudos

-1.98

POSITIVE LOGITS

of

2.75

we

2.72

ers

2.61

."

2.34

 they

2.09

 though

2.03

1.98

 once

1.93

for

1.84

the

1.83

Activations Density 0.008%