INDEX

Explanations

people and things involved

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

 الا

1.74

기

1.67

 μην

1.65

 perfectly

1.58

 brave

1.55

াই

1.54

 tired

1.54

 flowing

1.52

’

1.52

 fitted

1.50

POSITIVE LOGITS

ا

2.44

kannya

2.39

بینی

2.34

دت

2.33

та

2.30

քում

2.27

𝘥

2.19

2.14

es

2.11

te

2.11

Activations Density 0.013%