INDEX

Explanations

numbers and punctuation

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

saving

2.02

names

1.87

saver

1.81

sides

1.81

suits

1.78

defin

1.74

ten

1.69

了

1.67

self

1.67

 '*')

1.64

POSITIVE LOGITS

และ

2.66

 และ

2.56

và

2.53

،

2.50

 மற்றும்

2.38

 आणि

2.35

و

2.34

 وم

2.33

và

2.33

 มี

2.30

Activations Density 0.002%