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

pace

-0.31

åŃķæľŁ

-0.28

ingle

-0.27

çıŃçº§

-0.26

lify

-0.25

åŁºç¡Ģä¸Ĭ

-0.24

_MEDIA

-0.24

å¼±

-0.24

 Array

-0.24

lin

-0.24

POSITIVE LOGITS

SCO

0.36

Åĺ

0.27

 Bosch

0.27

 wishing

0.26

TEX

0.26

dependence

0.26

Ä°Åŀ

0.26

 flats

0.26

immel

0.25

 scratching

0.25

Activations Density 0.004%

No Known Activations

This feature has no known activations.