INDEX

Explanations

sequences starting with transition words

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

訌

-1.21

➚

-1.18

its

-1.18

空调

-1.18

țiuni

-1.15

ств

-1.14

 ratón

-1.13

 trasero

-1.12

駟

-1.11

 verand

-1.10

POSITIVE LOGITS

to

2.25

new

1.27

for

1.25

of

1.25

šo

1.23

 bēr

1.21

PRESA

1.20

 each

1.19

at

1.16

 after

1.14

Activations Density 0.315%