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

åĩłåı¥

-0.29

aris

-0.28

åĲĪæł¼

-0.26

æ¤įæłĳ

-0.25

AIM

-0.25

Attempt

-0.24

çĪ±ä½ł

-0.24

æĢİä¹Īè¯´

-0.23

Ford

-0.23

 Chamber

-0.23

POSITIVE LOGITS

icamente

0.28

ritos

0.26

eldo

0.26

opard

0.25

æĪ¬

0.24

.freeze

0.24

oggle

0.24

rant

0.24

raud

0.24

//~

0.23

Activations Density 0.021%

No Known Activations

This feature has no known activations.