INDEX

Explanations

numerical lists and suggestions

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

 annoying

1.35

ସ

1.32

 गिरा

1.22

峈

1.20

 onSuccess

1.16

 girlfriend

1.14

 первую

1.11

鋯

1.11

plays

1.10

 useless

1.10

POSITIVE LOGITS

ﺽ

1.27

Ве

1.18

on

1.14

 جبت

1.11

ün

1.07

 सप्टेंबर

1.06

 novem

1.05

大胆

1.04

 personnalité

1.04

 understandably

1.04

Activations Density 0.001%