INDEX

Explanations

spit fire / spitting truth

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

र्तन

1.29

졸

1.27

Há

1.21

 Règles

1.19

 Merkezi

1.18

ﺎ

1.17

erView

1.16

 आइए

1.16

 Обычно

1.15

이라는

1.14

POSITIVE LOGITS

ح

1.53

crawler

1.43

ро

1.34

П

1.33

centric

1.28

ון

1.27

mäß

1.27

й

1.27

 cuesta

1.25

誂

1.25

Activations Density 0.008%