INDEX

Explanations

anywhere followed by preposition

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

-3.14

的

-2.42

’

-2.39

⑉

-2.30

下面的

-2.22

糴

-2.20

 detenidos

-2.20

之为

-2.16

 剧照

-2.16

裃

-2.14

POSITIVE LOGITS

逦

2.88

AutoresizingMask

2.75

2.72

 They

2.61

↵↵

2.55

in

2.38

RUnlock

2.34

ଃ

2.33

)$,

2.25

)',

2.23

Activations Density 0.012%