INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ヒル

1.23

 Faithful

1.21

 наде

1.20

飯

1.19

美

1.17

风

1.12

 junt

1.12

 เก็บ

1.10

חד

1.10

Т

1.10

POSITIVE LOGITS

either

1.21

Either

1.16

 quelconque

1.16

 either

1.16

 Either

1.12

ITHER

1.08

liced

1.05

preferably

1.04

vió

1.02

 whatsoever

1.02

Activations Density 0.206%

No Known Activations