INDEX

Explanations

part of words, like in 'op', 'als'

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

ك

1.30

在

1.27

О

1.23

 affirme

1.21

 prefque

1.14

 électron

1.14

 interno

1.12

 chimiques

1.12

 cultivés

1.12

во

1.11

POSITIVE LOGITS

et

1.80

<0x80>

1.59

1.56

1.52

be

1.42

1.26

1.22

an

1.20

1.16

1.14

Activations Density 0.000%