INDEX

Explanations

left or top alignment

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

 宝宝

-1.32

迨

-1.27

 uiteindelijk

-1.27

汤

-1.20

 metu

-1.19

aların

-1.19

 inmiddels

-1.18

Kv

-1.17

bisous

-1.16

Кто

-1.15

POSITIVE LOGITS

1.61

 bądź

1.44

 mentre

1.43

ophageal

1.43

ibly

1.40

 cuales

1.35

/)

1.34

『

1.33

)++;

1.33

 mesmo

1.31

Activations Density 0.043%