INDEX

Explanations

pairs of words

lists of issues or advantages

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

 misma

0.46

"))

0.45

card

0.41

rh

0.41

Dit

0.41

idi

0.40

 précédemment

0.40

dit

0.40

words

0.39

ходом

0.38

POSITIVE LOGITS

 Organisations

0.56

 Offences

0.53

ाने

0.50

 नींव

0.50

 aque

0.49

 Lifting

0.49

᱓

0.49

 ईमित्र

0.48

થમ

0.47

했을

0.47

Activations Density 0.001%