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

 há»ģ

-0.27

ibly

-0.25

æĹłè®ºå¦Ĥä½ķ

-0.25

shed

-0.24

inally

-0.24

è´£ä»»ç¼ĸè¾ĳ

-0.24

åħ³éĹ¨

-0.24

habi

-0.23

 tá»ķ

-0.23

alist

-0.23

POSITIVE LOGITS

å²ŃåįĹ

0.28

HORT

0.27

 gathered

0.25

çĲ¼

0.25

gomery

0.24

 ourselves

0.23

è°Īèµ·

0.23

å°ĨåĨĽ

0.23

||(

0.23

Round

0.22

Activations Density 1.179%

No Known Activations

This feature has no known activations.