INDEX

Explanations

words followed by commas

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

<unused7>

0.71

()}")

0.70

<unused4>

0.69

 ఆట

0.68

̽

0.67

న్నీ

0.67

தியும்

0.66

$.\\

0.65

გრამ

0.64

इंदौर

0.64

POSITIVE LOGITS

,"

2.26

",

2.04

"",

2.03

,”

2.02

,'

2.00

",

1.97

',

1.93

'',

1.92

,",

1.89

“,

1.89

Activations Density 0.009%