INDEX

Explanations

starting point, characterization

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

staben

-1.35

standen

-1.30

 passos

-1.22

 secoli

-1.22

kalender

-1.22

我对

-1.21

hanced

-1.18

bilen

-1.18

铰

-1.17

gangen

-1.16

POSITIVE LOGITS

före

1.59

亟

1.39

for

1.32

 nuevamente

1.30

ansvar

1.28

miljø

1.25

👡

1.23

 کنیم

1.22

hbase

1.20

fören

1.15

Activations Density 0.108%