INDEX

Explanations

actions and targets

probabilities and distributions

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

忘

0.46

Dou

0.44

ற்காக

0.44

添

0.43

Dou

0.43

 Truly

0.42

ufl

0.42

 Suriname

0.42

遲

0.42

 Chile

0.42

POSITIVE LOGITS

voj

0.49

 saldır

0.47

מ

0.47

ApiCalls

0.45

 krwi

0.45

 relazioni

0.44

سے

0.44

 luisant

0.44

 stems

0.44

 govor

0.43

Activations Density 0.001%