INDEX

Explanations

technical explanations or lists

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

やお

1.24

iß

1.17

ettek

1.15

alagi

1.11

ь

1.10

or

1.10

ení

1.08

isée

1.08

aly

1.08

POSITIVE LOGITS

↵↵

2.16

↵↵↵

1.96

↵

1.89

↵↵↵↵

1.75

↵↵↵↵↵

1.69

 There

1.67

↵↵↵↵↵↵

1.66

‬

1.66

↵↵↵↵↵↵↵

1.65

 这是

1.60

Activations Density 0.725%