INDEX

Explanations

exact or same task/style/mechanisms

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

 tilby

0.67

自身的

0.65

 außerdem

0.63

 kendi

0.62

 erbjuder

0.61

 unlike

0.59

Unlike

0.58

 mempunyai

0.58

 oltre

0.58

 Unlike

0.56

POSITIVE LOGITS

 amount

1.42

 AMOUNT

1.14

amount

1.10

 Amount

1.09

 kind

1.08

 exact

1.06

 kinds

1.03

 amounts

1.01

 thing

1.00

 extent

0.99

Activations Density 2.575%