INDEX

Explanations

name then 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

<unused670>

1.34

<unused339>

1.33

<unused327>

1.32

<unused348>

1.31

<unused559>

1.27

<unused680>

1.26

<unused1869>

1.26

 regenv

1.25

<unused315>

1.25

<unused1039>

1.24

POSITIVE LOGITS

0.92

te

0.84

0.83

al

0.81

two

0.77

 five

0.77

six

0.75

mid

0.74

 train

0.73

all

0.73

Activations Density 0.000%