INDEX

Explanations

code comments and identifiers

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

-1.09

 якщо

-1.01

getvalue

-0.98

ofthe

-0.96

umnos

-0.96

 vienas

-0.93

 ясно

-0.93

']=

-0.92

μιουργ

-0.90

。

-0.90

POSITIVE LOGITS

ko

1.07

 также

1.04

1.03

ka

1.00

ja

0.97

のため

0.96

 TODO

0.96

 Ciebie

0.94

 подготовка

0.93

ks

0.92

Activations Density 0.071%