INDEX

Explanations

quantifying context and specific data

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

<0x80>

1.65

物资

1.49

ಿಗ

1.48

unw

1.39

imize

1.38

覧

1.37

 beware

1.35

 Thee

1.34

 Jewels

1.32

erry

1.30

POSITIVE LOGITS

л

3.19

в

2.16

te

2.02

ника

1.92

การ

1.91

jangan

1.88

iis

1.87

н

1.81

нали

1.77

ве

1.76

Activations Density 0.062%