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

åĪĨæĶ¯æľºæŀĦ

-0.30

erate

-0.29

çĽĬ

-0.29

åĨ²

-0.29

é¥²åħ»

-0.29

IPT

-0.27

Fn

-0.27

å¦»

-0.27

çľ¨çľ¼

-0.27

ÐµÐ³

-0.27

POSITIVE LOGITS

perienced

0.29

æľīæľŁ

0.28

<![

0.25

impan

0.25

olicies

0.24

 Protected

0.24

éªĪ

0.24

çķ¯

0.24

itere

0.23

æ¾Ī

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.