INDEX

Explanations

y/and followed by a verb

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

其他

2.28

か

2.22

ความ

2.03

 ακόμα

1.93

社会

1.92

ر

1.91

з

1.89

ع

1.84

 crónica

1.77

때

1.77

POSITIVE LOGITS

 whatnot

2.05

romeda

1.98

ंगाबाद

1.64

ায়

1.57

 sebagainya

1.57

radiative

1.56

 secondly

1.55

 Subsidi

1.45

▉

1.40

lng

1.38

Activations Density 1.353%