INDEX

Explanations

start of quote or "I" / "we":

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

 conocidas

-1.52

 podjet

-1.37

 establecidas

-1.37

 difíciles

-1.33

 Badezimmer

-1.32

 ABBREVIATIONS

-1.32

Hrsg

-1.31

⇿

-1.30

 esos

-1.30

 indicaciones

-1.27

POSITIVE LOGITS

for

1.84

 when

1.51

 then

1.50

 wein

1.34

 для

1.31

他の

1.29

</h2>

1.27

 frites

1.21

of

1.21

quando

1.20

Activations Density 0.004%