INDEX

Explanations

academic thesis or dissertation

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

was

-2.59

!"

-2.50

 الرخصة

-2.42

︕

-2.25

!»

-2.16

 unſ

-2.13

are

-2.13

*/

-2.11

ارتمان

-2.11

»,

-2.09

POSITIVE LOGITS

 zusätzlichen

2.34

 doppelt

2.05

 ungewöhn

1.95

 Züge

1.90

 evidenced

1.89

).

1.88

1.81

 gewöhn

1.81

in

1.80

Activations Density 0.011%