INDEX

Explanations

detect, analyze, consult

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

颖

1.43

 contamos

1.37

ための

1.36

}$=

1.33

 délégation

1.32

さは

1.30

&=&\

1.29

}})^{

1.27

 disampaikan

1.27

elenggarakan

1.27

POSITIVE LOGITS

ตรวจสอบ

1.49

detect

1.42

consult

1.38

╝

1.37

 detect

1.34

explicit

1.33

 analyze

1.32

analyze

1.32

 Consult

1.31

 explicitly

1.30

Activations Density 0.161%