INDEX

Explanations

run specific technical terms

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

おわりに

-1.44

 Tentang

-1.35

出来た

-1.33

 ήταν

-1.31

 nejsou

-1.27

👢

-1.27

 вновь

-1.24

خخ

-1.24

sigkeit

-1.23

 tendrás

-1.23

POSITIVE LOGITS

run

1.57

ran

1.55

run

1.55

running

1.52

 running

1.52

 runs

1.51

ри

1.40

RUN

1.39

ecé

1.34

RUN

1.33

Activations Density 0.109%