INDEX

Explanations

starts sentences with "I"

ai chatbot disclaimer

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

 nói

0.42

 ज़र

0.41

 речи

0.41

ανά

0.40

 говорю

0.39

gifs

0.38

ቂ

0.38

 analogy

0.38

विश्व

0.37

指的是

0.37

POSITIVE LOGITS

za

0.51

 consent

0.49

uko

0.48

ru

0.47

 Consent

0.47

uri

0.46

鸨

0.46

hu

0.44

ken

0.43

ca

0.43

Activations Density 0.023%