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

boxed

-0.30

 Shack

-0.26

...\

-0.26

eing

-0.25

æ±ª

-0.23

ee

-0.23

huge

-0.23

each

-0.23

æľŁæľĽ

-0.22

åĵ½

-0.22

POSITIVE LOGITS

elden

0.25

 negotiate

0.24

ivity

0.24

 introdu

0.24

plevel

0.23

lt

0.23

Rat

0.23

 negotiated

0.22

 invited

0.22

æ³¨æĦıåĬĽ

0.22

Activations Density 0.002%

No Known Activations

This feature has no known activations.