INDEX

Explanations

expressions with parentheses and negative numbers

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

NewUrlParser

0.38

bottlecap

0.38

 SCGS

0.37

भाविक

0.37

+++++++++#

0.37

螻

0.36

 detoxification

0.36

 bull

0.35

চৈতন্য

0.35

 চৈতন্য

0.35

POSITIVE LOGITS

(-

3.14

`-

2.88

(-

2.80

[-

2.72

$(-

2.72

$-

2.61

"-

2.56

'-

2.53

{-

2.42

}(-

2.38

Activations Density 0.246%