INDEX

Explanations

generative adversarial networks, reinforcement learning, attention

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

Commentaires

-0.80

zeko

-0.78

 Mauro

-0.77

过来的

-0.73

agami

-0.72

 Aval

-0.71

posX

-0.70

۟

-0.70

дмила

-0.69

伟大的

-0.69

POSITIVE LOGITS

 attention

1.25

attention

1.18

BERT

1.12

Attention

1.05

 reinforcement

0.96

 Attention

0.96

 neural

0.94

GAN

0.91

モデル

0.91

 model

0.89

Activations Density 0.048%