INDEX

Explanations

verbs followed by words

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

 möjlighet

-1.55

僦

-1.38

odenal

-1.34

 secreta

-1.31

 verkligen

-1.30

ಿದೆ

-1.27

 wadah

-1.25

 '.';

-1.24

-1.23

;//

-1.21

POSITIVE LOGITS

if

2.11

be

2.03

we

1.59

我们

1.58

of

1.57

This

1.41

1.39

1.38

get

1.36

but

1.31

Activations Density 0.047%