INDEX

Explanations

after

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

äºĭåħĪ

-0.09

èĩªä»İ

-0.08

hurst

-0.08

 actuellement

-0.08

äºĭåīįãģ«

-0.07

é¢ĦåħĪ

-0.07

çİ°åľ¨å·²ç»ı

-0.07

 heut

-0.07

 currently

-0.07

 actualmente

-0.07

POSITIVE LOGITS

ä¸įä¹ħçļĦ

0.11

çļĦä¸Ģæ®µæĹ¶éĹ´

0.11

éģĹçĹĩ

0.10

ä¸įä¹ħ

0.10

æīįåıĳçİ°

0.10

 ÙĪÙĤØ¨ÙĦ

0.10

ç´§æİ¥çĿĢ

0.10

å¾Īéķ¿ä¸Ģæ®µæĹ¶éĹ´

0.09

æ²¡å¤ļä¹ħ

0.09

æīįçŁ¥éģĵ

0.09

Activations Density 0.132%