INDEX

Explanations

names followed by verbs

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

0.40

↵↵

0.37

Attenuation

0.34

0.33

Let

0.32

なくなる

0.32

 attenuation

0.32

Rightarrow

0.32

 সুতরাং

0.31

Let

0.31

POSITIVE LOGITS

 began

0.55

 went

0.54

 telah

0.53

had

0.51

 tenía

0.51

 collaborated

0.51

 knew

0.50

 oversaw

0.50

 believes

0.50

 undertook

0.49

Activations Density 0.231%