INDEX

Explanations

expects followed by varied phrases

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

ле

1.53

د

1.48

 mastect

1.40

 encarg

1.35

д

1.34

 limo

1.32

。

1.31

 abide

1.27

 распространен

1.26

گي

1.25

POSITIVE LOGITS

2.13

ado

1.78

ation

1.42

ac

1.41

se

1.38

est

1.36

ly

1.32

ها

1.32

ade

1.30

sp

1.30

Activations Density 0.001%