INDEX

Explanations

confirming understanding

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

嗕

1.26

 programm

1.22

ᑉ

1.20

嗗

1.19

 τῶν

1.19

亾

1.14

嗘

1.13

^{*},

1.12

 कॉनकॉर्ड

1.12

₁,

1.12

POSITIVE LOGITS

icious

1.28

Would

1.25

อะไร

1.15

Does

1.13

อาการ

1.12

This

1.08

Brist

1.07

Another

1.06

ajj

1.06

 Would

1.06

Activations Density 0.009%