INDEX

Explanations

mass + negative consequences

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

 Propositions

1.69

1.45

1.39

い

1.38

 Town

1.38

ü

1.38

и

1.33

่

1.33

ا۔

1.31

，

1.30

POSITIVE LOGITS

yelination

1.39

talking

1.30

 medall

1.27

นิด

1.27

აციის

1.26

elina

1.26

ına

1.25

ભગ

1.25

tte

1.23

mmm

1.23

Activations Density 0.003%