INDEX

Explanations

causal conjunctions like because

because, but, because, but

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

🗓

0.50

represents

0.48

sequence

0.45

_{

0.45

рован

0.44

','$

0.43

0.42

------------

0.42

᾿

0.42

POSITIVE LOGITS

 gdyż

0.66

 omdat

0.64

 because

0.64

 γιατί

0.63

 deoarece

0.62

 které

0.61

因為

0.60

 BECAUSE

0.59

 protože

0.57

 لأن

0.57

Activations Density 0.223%