INDEX

Explanations

multiple languages

The neuron flags tokens containing non-English or non-ASCII character sequences (e.g. accented, CJK, Cyrillic, Hangul, Vietnamese diacritics, etc.).

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

 тебя

1.48

 тебе

1.48

 तुझ्या

1.47

 тво

1.42

 тобі

1.34

 तुझे

1.31

 அவன்

1.29

thy

1.24

 ngươi

1.23

 тобой

1.21

POSITIVE LOGITS

 입니다

3.13

입니다

3.08

 있습니다

2.75

 것입니다

2.66

です

2.63

ค่ะ

2.56

였습니다

2.53

 합니다

2.48

합니다

2.41

ครับ

2.39

Activations Density 0.077%