INDEX

Explanations

nouns followed by descriptive 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

lysm

-1.44

.‏

-1.41

brtc

-1.36

以及

-1.29

 была

-1.28

。

-1.24

and

-1.23

unno

-1.22

greja

-1.18

zyny

-1.18

POSITIVE LOGITS

 that

2.88

 που

1.68

of

1.63

 whose

1.53

 must

1.50

who

1.48

ที่มี

1.42

can

1.41

may

1.40

 should

1.38

Activations Density 0.106%