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

 insign

-0.28

MISSION

-0.26

inel

-0.26

 Kens

-0.24

çļĦåı¯èĥ½æĢ§

-0.23

-feedback

-0.23

 aborted

-0.23

Ð²Ð°Ñı

-0.23

æĶ»åĿļæĪĺ

-0.23

CB

-0.23

POSITIVE LOGITS

_screen

0.30

ora

0.25

exc

0.25

è´ŁåĢº

0.25

ongan

0.24

äººæīįéĺŁä¼į

0.24

 closets

0.24

 Platz

0.24

proc

0.24

rians

0.24

Activations Density 0.882%

No Known Activations

This feature has no known activations.