INDEX

Explanations

Reinforcement Learning

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

𝐥

3.37

𝐦

3.24

𝗶

3.15

𝐢

3.06

𝗺

3.03

izumab

3.01

 mounts

3.01

ставки

2.92

 thumbnails

2.87

Seats

2.84

POSITIVE LOGITS

뮐

2.01

fra

1.93

ed

1.92

ði

1.92

ותו

1.87

 giov

1.85

chains

1.81

ுள்ளார்

1.80

துவாக

1.79

탈

1.79

Activations Density 0.012%