INDEX

Explanations

programming variables

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

 nadru

-1.61

 koneksi

-1.56

 vieron

-1.56

なんですよ

-1.47

為に

-1.40

 kré

-1.40

etui

-1.38

cannabis

-1.37

spricht

-1.36

 zelve

-1.36

POSITIVE LOGITS

can

1.43

1.34

1.24

1.23

 could

1.23

つまり

1.17

マンガ

1.16

アンサー

1.15

がある

1.14

が

1.12

Activations Density 0.010%