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

(Expected

-0.29

ogram

-0.28

å®ļéĩı

-0.28

still

-0.28

ohana

-0.27

 Stack

-0.26

æİ§

-0.25

Still

-0.25

-align

-0.25

ead

-0.24

POSITIVE LOGITS

èĢ³

0.29

zego

0.27

 Mixer

0.25

åģļåĪ°äºĨ

0.25

åĮħ

0.24

æªĶ

0.24

æĪĳä»¬å¿ħé¡»

0.24

èĥ¸

0.23

å¯»å¸¸

0.23

è¿Ļä¹Īåģļ

0.23

Activations Density 0.002%

No Known Activations

This feature has no known activations.