INDEX

Explanations

conversational transition words

direct, casual conversational cues—especially second-person address and short social/emotional prompts in user queries.

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 приве

0.26

ಖ

0.25

 வைர

0.25

 prolific

0.25

miR

0.24

 الإ

0.24

Threat

0.24

пла

0.24

Lim

0.24

 desider

0.24

POSITIVE LOGITS

 lakini

0.33

 nhưng

0.33

 ngunit

0.31

 pero

0.31

 mutta

0.31

 сегодня

0.30

 但是

0.30

 কিন্তু

0.30

ьогодні

0.30

?/

0.30

Activations Density 0.336%