INDEX

Explanations

architectural works and details

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

芏

1.68

 panning

1.60

 goodbye

1.55

 Goodbye

1.54

 quadrupole

1.54

 locus

1.53

ধবার

1.51

 eddy

1.48

পত্র

1.45

comparator

1.44

POSITIVE LOGITS

К

1.44

,”

1.40

offe

1.40

 dared

1.35

ulz

1.34

he

1.33

dream

1.31

mentare

1.30

SHARED

1.30

,“

1.29

Activations Density 0.000%