INDEX

Explanations

all information, humans, links, rules

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

り

3.13

いた

2.61

कर

2.59

сть

2.39

ação

2.33

ように

2.31

daki

2.31

서

2.28

name

2.17

rifice

2.16

POSITIVE LOGITS

iż

1.97

িখিত

1.93

 dicas

1.82

 Comerc

1.78

 horas

1.74

uwen

1.69

써

1.68

 trừ

1.66

bearers

1.65

儘

1.65

Activations Density 0.077%