INDEX

Explanations

motivational and engaging words

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

дела

0.45

hiddenMap

0.43

בו

0.42

쿼

0.42

 annotate

0.42

 പ്രസി

0.42

ай

0.41

ัย

0.41

 হীরু

0.40

inFile

0.40

POSITIVE LOGITS

 motivation

1.13

 motiv

1.09

 motivate

1.09

 persuade

1.08

 Motivation

1.08

 incentives

1.06

 persuasion

1.04

 incentiv

1.03

 Incent

1.02

 incentive

1.02

Activations Density 0.499%