INDEX

Explanations

Q: questions or node types

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

-3.27

-2.55



-2.44

葙

-2.44

”.

-2.42

饪

-2.41

 produs

-2.25

 grigio

-2.16

’

-2.13

 danne

-2.11

POSITIVE LOGITS

買う

2.30

 erstaun

2.16

女兒

2.16

 applaud

2.08

 veinte

2.08

 применя

2.05

he

2.05

 faszin

2.00

五个

1.98

小时候

1.97

Activations Density 0.000%