INDEX

Explanations

effective, doubt, cliff, hard, good, friends, severe

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

つづく

-1.32

 such

-1.27

 like

-1.21

為に

-1.19

 filós

-1.16

 buoni

-1.09

 solcher

-1.07

 devrez

-1.05

ためには

-1.04

綺麗に

-1.02

POSITIVE LOGITS

などが

1.27

や

1.16

理論

1.15

or

1.13

domada

1.08

などを

1.06

 menonton

1.06

規模

1.03

糧

1.01

 нови

1.00

Activations Density 0.010%