INDEX

Explanations

code

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 reachable

-0.28

=?,

-0.28

noinspection

-0.27

VI

-0.26

çĬ¯

-0.25

åı°ä¸Ĭ

-0.25

 rest

-0.25

å¹³åĿĩæ¯ı

-0.25

arnings

-0.25

ARA

-0.25

POSITIVE LOGITS

otion

0.28

ollipop

0.26

llx

0.24

 THAN

0.23

ssi

0.23

 aston

0.23

gow

0.23

 tá»īnh

0.23

ility

0.22

 northern

0.22

Activations Density 0.009%