INDEX

Explanations

code related to locking

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

 Wikimedijinoj

-0.70

 Majefty

-0.65

 myſelf

-0.65

存于互联网档案馆

-0.64

 pleaſure

-0.63

 stiefel

-0.62

ſelf

-0.61

 themſelves

-0.61

 fometimes

-0.60

 Simult

-0.60

POSITIVE LOGITS

Дереккөздер

0.65

basicConfig

0.63

lock

0.60

 Gris

0.60

awancara

0.58

<bos>

0.57

LOCK

0.54

флек

0.50

 TextAppearance

0.49

softc

0.49

Activations Density 0.001%