INDEX

Explanations

if condition checking

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

máy

-1.34

Neden

-1.23

bình

-1.13

İyi

-1.11

Díky

-1.08

쩡

-1.07

Další

-1.05

 damaligen

-1.04

giày

-1.03

Proč

-1.03

POSITIVE LOGITS

not

1.27

no

1.27

 multiple

1.17

 oluşan

1.13

any

1.11

 aint

1.02

 dont

0.96

ません

0.93

む

0.93

 this

0.91

Activations Density 0.021%