INDEX

Explanations

persuasion and persuasive

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

 lured

0.52

鼓励

0.46

 lures

0.46

 encourage

0.45

鼓勵

0.43

 प्रोत्साहित

0.43

 entice

0.42

 Encourage

0.42

 encouraging

0.41

鑊

0.41

POSITIVE LOGITS

 Pers

1.84

 persuasion

1.78

Pers

1.70

 persuasive

1.64

 pers

1.61

pers

1.58

 PERS

1.46

 persuas

1.43

PERS

1.38

 persuade

1.23

Activations Density 0.026%