INDEX

Explanations

academic and technical documents

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

so

-0.95

 deliberately

-0.90

cestry

-0.87

 Invent

-0.83

 believe

-0.82

 still

-0.81

to

-0.80

 even

-0.80

 here

-0.77

 within

-0.77

POSITIVE LOGITS

為に

1.02

様な

1.02

ために

1.00

LLS

0.98

 Wartung

0.90

 principios

0.88

がっ

0.87

 bestehenden

0.87

 Colombo

0.83

activité

0.82

Activations Density 0.000%

No Known Activations