INDEX

Explanations

when

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

åį³ä½¿æĺ¯

-0.27

å·²æľī

-0.27

oir

-0.26

å°±æľī

-0.26

 devoted

-0.25

 nature

-0.25

åıĪæľī

-0.25

å·²ç»ıæľī

-0.25

olar

-0.25

åıªè¦ģæľī

-0.25

POSITIVE LOGITS

æĪĳæĥ³

0.26

åĽ½æĹĹ

0.26

ripp

0.26

çŁ¥ãģ£ãģ¦

0.25

AreaView

0.24

 undercut

0.24

çĽ®ãģ«

0.24

ulton

0.24

è¦ģèĢĥèĻĳ

0.23

åĲĥçļĦ

0.23

Activations Density 0.006%