INDEX

Explanations

variables followed by parentheses or exponents

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

 have

-1.74

häuse

-1.40

menade

-1.39

리가

-1.36

CLUDING

-1.32

راهيم

-1.31

 biasanya

-1.27

 有限

-1.27

大王

-1.27

 бассей

-1.23

POSITIVE LOGITS

1.45

<em>

1.39

1.38

地说道

1.32

を行います

1.27

も行

1.25

ul

1.22

1.20

つづく

1.19

 plucked

1.18

Activations Density 0.170%