INDEX

Explanations

verbs introducing reported speech

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

 quedando

0.20

 oriented

0.19

 gjorde

0.19

 কাজেই

0.18

 assortment

0.17

 urination

0.17

 secondo

0.17

 denoting

0.17

 sebagainya

0.17

 ranging

0.17

POSITIVE LOGITS

 rằng

0.26

 bahwa

0.25

 ότι

0.25

 that

0.23

 bahawa

0.21

 که

0.21

that

0.21

 thay

0.19

ਕ

0.19

이

0.19

Activations Density 0.217%