INDEX

Explanations

comma followed by "-ing" words

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

ifiably

1.22

ד

1.17

ご

1.14

ও

1.11

锏

1.08

ש

1.07

life

1.03

<bos>

1.01

 вами

1.00

 सवार

1.00

POSITIVE LOGITS

 allowing

1.34

 evade

1.22

 allows

1.15

 anticipate

1.12

 providing

1.12

hluk

1.11

 numbering

1.08

 creating

1.07

 culminates

1.06

 adhere

1.06

Activations Density 0.005%