INDEX

Explanations

here's a breakdown/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

Examples

0.86

examples

0.81

例えば

0.79

example

0.77

そのような

0.77

 etmektedir

0.76

たとえば

0.74

 esempi

0.71

 beispielsweise

0.71

 exempel

0.70

POSITIVE LOGITS

 spoiler

1.15

 Spoiler

1.15

 buckle

1.12

 prepping

1.06

 prepare

1.01

 Prepare

1.00

 figuring

0.97

 Here

0.96

 here

0.95

 caveat

0.94

Activations Density 0.671%