INDEX

Explanations

describing subjective states after felt

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

 thuộc

1.15

 çeşitli

1.11

 számos

1.11

 Truy

1.10

)|$(

1.09

∞</

1.09

 thành

1.08

𝐤

1.08

 অন্তর্গত

1.08

𝐫

1.08

POSITIVE LOGITS

 because

1.16

 لأ

1.13

but

1.13

 runny

1.08

 लेकिन

1.07

 क्योंकि

1.04

 hurtful

1.03

 але

1.02

 that

1.01

ل

0.99

Activations Density 1.707%