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

æľ¬äºº

-0.32

äºİ

-0.28

 extensions

-0.27

extensions

-0.27

newline

-0.27

éĢĨè½¬

-0.26

avatars

-0.26

 grandparents

-0.26

ä¸Ģäºº

-0.26

extends

-0.25

POSITIVE LOGITS

éªħ

0.26

 scientifically

0.25

å¸ĤåĮº

0.25

æľīæĿ¡ä»¶çļĦ

0.25

åħīçº¤

0.25

<$

0.24

åĬ¡å®ŀ

0.24

ç»Ŀç¼ĺ

0.24

.splice

0.24

æŃ£æĺ¯åĽłä¸º

0.24

Activations Density 0.009%

No Known Activations

This feature has no known activations.