INDEX

Explanations

experiment

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

opan

-0.08

å®Ĺå¸Ī

-0.07

éģįéĩİ

-0.07

åħ¥åŃ¦èĢĥè¯ķ

-0.07

æ·±çŁ¥

-0.07

 fallback

-0.06

å¤ļå¹´

-0.06

 maquinaria

-0.06

æł¼å±Ģ

-0.06

éĶ»éĢł

-0.06

POSITIVE LOGITS

 experiment

0.13

 Experiment

0.12

Experiment

0.11

å®ŀéªĮä¸Ń

0.11

periment

0.11

å®ŀéªĮ

0.11

experiment

0.10

 Versuch

0.10

çļĦå®ŀéªĮ

0.10

 ÑįÐºÑģÐ¿ÐµÑĢÐ¸Ð¼

0.09

Activations Density 0.029%