INDEX

Explanations

HSK, hack databases, hypothetical

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

ሖ

1.22

 хорошее

1.17

 hukum

1.14

SSP

1.14

 hyperfine

1.14

 جمله

1.12

 высоту

1.11

 совсем

1.10

 উপযুক্ত

1.07

hard

1.05

POSITIVE LOGITS

 sapiens

2.01

gxh

1.69

 pylori

1.57

萏

1.44

izontal

1.43

élène

1.41

aplic

1.39

چل

1.35

ysuckle

1.34

ಬ್ಬಳ್ಳಿ

1.30

Activations Density 0.751%