INDEX

Explanations

not or is not

negation or negative words

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

했고

0.49

 পাইয়া

0.45

と共に

0.43

 있다

0.43

ಾಗಿದೆ

0.42

获得了

0.42

 जेव्हा

0.41

 করিয়াছি

0.41

었고

0.41

 করেছি

0.40

POSITIVE LOGITS

 نہیں

1.37

 نہیں۔

1.33

 नहीं

1.31

 bukanlah

1.25

 değildir

1.23

 ਨਹੀਂ

1.20

 없습니다

1.16

வதில்லை

1.13

 ikke

1.09

 nėra

1.09

Activations Density 0.202%