INDEX

Explanations

key, lock, unlock, opener, combinations

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

it

-1.55

-1.45

</sub>

-1.43

in

-1.43

you

-1.40

 verste

-1.35

куп

-1.30

 видит

-1.26

 sure

-1.25

</u>

-1.21

POSITIVE LOGITS

canza

1.41

图案

1.38

憮

1.34

隶

1.30

 каждый

1.30

Недо

1.30

who

1.27

扨

1.26

湣

1.25

 довольно

1.23

Activations Density 0.035%