INDEX

Explanations

social media queries

Option 1: explanations

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 sentient

0.46

 artis

0.46

 carnival

0.44

儸

0.44

 barons

0.43

يدا

0.42

 ured

0.42

زمانہ

0.42

 aristocracy

0.41

UREG

0.41

POSITIVE LOGITS

↵↵↵

0.54

<blockquote>

0.52

<eos>

0.51

↵↵↵↵↵

0.51

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

0.51

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

0.50

↵↵↵↵

0.49

↵↵↵↵↵↵↵↵↵

0.49

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

0.49

</h4>

0.49

Activations Density 0.104%