INDEX

Explanations

"below" followed by explanation

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

к

0.35

ன்

0.28

ט

0.27

از

0.26

]);

0.26

 Münster

0.24

لیف

0.24

ط

0.24

ブ

0.24

POSITIVE LOGITS

 gaming

0.25

nings

0.24

pping

0.24

ø

0.24

 assass

0.24

 agot

0.24

 malice

0.23

at

0.23

ill

0.23

 graph

0.23

Activations Density 0.009%