INDEX

Explanations

We compare, we can, we will

we can chat

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

 sentimos

0.63

 ourselves

0.62

 저희

0.59

Unsere

0.57

 અમને

0.54

 nuestras

0.53

 nossas

0.52

 हमारी

0.52

给我们

0.51

 שלנו

0.50

POSITIVE LOGITS

 میرے

0.50

 discussion

0.47

 mutually

0.46

 convergence

0.45

討論

0.45

 আমাকে

0.45

 chat

0.44

 mijn

0.43

 തമ്മ

0.42

মাস

0.41

Activations Density 0.060%