INDEX

Explanations

code output followed by numbers

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

ྩ

3.54

CAUSE

3.02

்க

2.97

dup

2.79

 Totally

2.75

 ува

2.74

מש

2.72

ྫ

2.72

 chattel

2.71

$}

2.64

POSITIVE LOGITS

ጨማሪ

3.23

ال

3.19

ے

3.18

nial

2.92

큰

2.89

و

2.87

itating

2.82

>(_

2.77

<0x80>

2.71

 kaž

2.70

Activations Density 0.793%