INDEX

Explanations

word or symbol followed by punctuation

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

𝐢

2.88

𝐲

2.85

𝐥

2.80

𝐠

2.77

➜

2.61

ب

2.52

isPlaying

2.49

𝐜

2.36

𝐑

2.32

ように

2.31

POSITIVE LOGITS

 tahu

2.71

idot

2.69



2.52

 legjob

2.52



2.45

^{*}

2.39

judicial

2.35

 intent

2.34

σι

2.34

 sekali

2.34

Activations Density 0.334%