INDEX

Explanations

Code snippets

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

 vibrator

-0.31

-shop

-0.26

_shop

-0.26

å°±åı¯ä»¥äºĨ

-0.25

åį³åı¯

-0.25

]++;↵

-0.25

ç²ī

-0.25

å°±å¤ŁäºĨ

-0.24

èī³

-0.24

ç»Īäºİ

-0.24

POSITIVE LOGITS

æİĴè¡Į

0.28

iline

0.28

Bir

0.26

ãģĵãģ¡ãĤī

0.25

çĸĶ

0.24

Named

0.24

technical

0.24

 Reve

0.24

 technically

0.24

 Identifier

0.23

Activations Density 0.000%