INDEX

Explanations

one, ONE, Tea, FIG, Ang

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

to

-1.94

on

-1.66

for

-1.56

the

-1.49

 when

-1.47

up

-1.37

ly

-1.33

at

-1.30

liegenden

-1.28

 eventuell

-1.25

POSITIVE LOGITS

емым

1.39

 quirk

1.34

 cabelo

1.33

之心

1.30

 менять

1.27

 That

1.27

ोंने

1.25

Ine

1.25

珰

1.24

 ребенок

1.23

Activations Density 0.036%