INDEX

Explanations

referring to self and group

we, our, us

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

在我

0.51

 είχε

0.48

 conmigo

0.47

was

0.47

 your

0.47

和我

0.46

্ত

0.45

 আমাকে

0.45

僕は

0.44

मैंने

0.44

POSITIVE LOGITS

 ourselves

2.16

 можем

1.48

如果我们

1.43

 хотим

1.40

 знаем

1.39

 nossas

1.38

 우리는

1.33

 우리의

1.32

当我们

1.32

 nuestros

1.31

Activations Density 0.304%