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

GD

-0.27

otes

-0.26

 Bates

-0.25

cour

-0.25

odore

-0.25

æĹ¥è®¯

-0.25

ffee

-0.25

çĽ¸

-0.25

×ķ×ª

-0.25

icity

-0.24

POSITIVE LOGITS

 Highlander

0.26

 varied

0.26

arily

0.25

naz

0.24

vary

0.24

 varying

0.24

éĶ¡

0.24

serialize

0.24

warts

0.24

iland

0.24

Activations Density 0.002%

No Known Activations

This feature has no known activations.