INDEX

Explanations

-ation / -ization suffixes

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Negative Logits

ary

0.61

ally

0.54

ARY

0.50

ARIES

0.42

ists

0.41

甲基

0.37

arya

0.35

aryl

0.35

 Zebra

0.35

als

0.35

POSITIVE LOGITS

lač

0.36

 proposition

0.36

 propositions

0.35

 เฉ

0.35

 artich

0.34

solutions

0.34

 શકો

0.34

 Propositions

0.34

 žen

0.33

 immunized

0.33

Activations Density 0.002%

No Known Activations