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

joined

-0.28

 appBar

-0.25

äº¤ä»£

-0.25

Ã¨s

-0.24

ä»İæĿ¥æ²¡

-0.24

 AppBar

-0.23

kho

-0.23

 joined

-0.23

æĬĬæı¡

-0.23

 HACK

-0.23

POSITIVE LOGITS

æ¢Ń

0.26

/xhtml

0.26

ogi

0.26

aud

0.26

 auss

0.25

-Methods

0.25

çĶŁäº§è®¾å¤ĩ

0.25

ROLL

0.25

imon

0.25

ä¸ĭçıŃ

0.24

Activations Density 0.003%

No Known Activations

This feature has no known activations.