INDEX

Explanations

authority, authenticity, authoritarianism

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

து

1.44

 enterprise

1.28

या

1.26

 važ

1.25

ة

1.24

ય

1.23

ethe

1.17

ed

1.15

 improvement

1.10

getPage

1.10

POSITIVE LOGITS

itatively

1.75

itatea

1.54

IDADES

1.34

itative

1.34

 vadd

1.32

oid

1.32

 било

1.29

 ব্যক্তিদের

1.22

sparsebundle

1.19

以降

1.18

Activations Density 0.051%