INDEX

Explanations

code elements and types

commas separating function parameters in code.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 Meksi

-1.96

⛔

-1.82

 作り方

-1.79

柠檬

-1.74

’，

-1.74

 ſever

-1.73

🕗

-1.73

 idyl

-1.68

Введение

-1.63

‘’

-1.60

POSITIVE LOGITS

 that

2.77

 with

2.17

 this

1.73

for

1.73

in

1.72

can

1.70

1.59

or

1.58

 тази

1.56

 tohto

1.52

Activations Density 0.028%