INDEX

Explanations

now followed by a verb

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

of

-1.70

 then

-1.68

 όμως

-1.35

 mindig

-1.34

 Ahnung

-1.33

 Rücksicht

-1.33

 siempre

-1.27

 pensez

-1.27

 stets

-1.24

 azonban

-1.24

POSITIVE LOGITS

 более

1.49

rounder

1.45

 emporio

1.41

 другие

1.38

 istället

1.27

 olika

1.25

 більш

1.20

^{}

1.19

 blauwe

1.18

 året

1.17

Activations Density 0.275%