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

è£ħè½½

-0.29

ilty

-0.26

odel

-0.24

åľ°ä½į

-0.23

orre

-0.23

çļĦåľ°

-0.23

åºĶä»ĺ

-0.23

-break

-0.23

çĮ¬

-0.23

 Kaplan

-0.23

POSITIVE LOGITS

 Shiite

0.28

zw

0.27

èĩªçĦ¶æĺ¯

0.27

æ·³

0.26

 strips

0.26

REEN

0.25

 Miss

0.25

 Hornets

0.24

_UTF

0.24

reen

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.