INDEX

Explanations

reflexive pronouns followed by verbs

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

ن

2.32

ﺯ

1.89

1.83

ного

1.66

tedir

1.64

nimi

1.57

$("

1.49

allele

1.49

hasil

1.48

nymi

1.48

POSITIVE LOGITS

л

1.96

schaft

1.42

াজে

1.38

ोदर

1.34

mpg

1.32

 будет

1.28

്യം

1.27

<0xA6>

1.27

 несо

1.25

元的

1.24

Activations Density 0.033%