INDEX

Explanations

No Explanations Found

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

ä¾¿äºİ

-0.28

æ£Ģå¯Ł

-0.28

åĨ²

-0.28

æį¢

-0.28

ABC

-0.27

ãĢĤ

-0.27

åīįè¿Ľ

-0.26

tle

-0.25

çľŁ

-0.25

ç«ĭåľº

-0.25

POSITIVE LOGITS

ouns

0.28

ukes

0.27

|_

0.27

éĺŁåĳĺä»¬

0.26

richt

0.26

ÙĬØ¨

0.26

 Peak

0.26

 proteins

0.25

 spans

0.25

[|

0.25

Activations Density 0.021%

No Known Activations

This feature has no known activations.