INDEX

Explanations

but followed by pronouns or question 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

াল

1.24

ড

1.07

щения

1.04

不

1.03

स

1.03

在这种

1.00

и

0.97

ح

0.97

व

0.94

вни

0.93

POSITIVE LOGITS

thole

1.57

termilk

1.40

 digress

1.39

 alas

1.32

 néanmoins

1.27

𝑑

1.11

𝑛

1.05

tered

1.02

𝑥

1.01

lers

1.00

Activations Density 0.431%