INDEX

Explanations

red colors or concepts

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

ن

1.38

nın

1.25

 extrémités

1.24

 huile

1.23

 juist

1.23

лни

1.22

我想

1.20

দিক

1.18

tow

1.16

 pared

1.16

POSITIVE LOGITS

")

1.62

"]

1.57

 tinge

1.47

"].

1.46

ಯೇ

1.40

">

1.33

"]);

1.31

">(</

1.30

hate

1.30

")]

1.26

Activations Density 0.154%