INDEX

Explanations

# and dialogue starters

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

 وج

1.55

スコ

1.53

デイ

1.40

コー

1.36

などを

1.33

ス

1.33

 Dioc

1.30

유

1.29

ัด

1.28

デ

1.27

POSITIVE LOGITS

rinsic

1.93

 handlerInput

1.75

<end_of_image>

1.72

1.66

1.63

penas

1.62

1.61

nicki

1.59

resonant

1.59

 Majka

1.57

Activations Density 0.153%