INDEX

Explanations

json structure with specific fields

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

the

1.30

ihe

1.28

 journalist

1.12

 adaptability

1.09

rawa

1.05

 those

1.05

rowski

1.04

 journalists

1.04

✐

1.03

 হইলেই

1.00

POSITIVE LOGITS

ನ್

1.23

 کردہ

1.17

های

1.16

<0xBA>

1.13

tive

1.12

<bos>

1.11

ları

1.11

incere

1.11

entire

1.07

めちゃ

1.07

Activations Density 0.272%