INDEX

Explanations

graduate and postgraduate degrees

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

 pale

-0.76

 arrancar

-0.75

tplatz

-0.73

-0.71

 декора

-0.71

 Historical

-0.70

 polo

-0.70

 random

-0.68

hexane

-0.68

 project

-0.66

POSITIVE LOGITS

 graduate

1.70

 postgraduate

1.46

Graduate

1.38

graduate

1.29

 Graduate

1.23

 Postgraduate

1.09

Masters

1.07

 doctoral

1.04

研究生

1.02

ADUATE

1.00

Activations Density 0.027%