INDEX

Explanations

specific nouns 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

😍😍

0.95

😭😭

0.91

😀

0.86

 anisot

0.83

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

0.83

↵↵↵↵↵↵↵↵↵

0.82

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

0.81

↵↵↵↵↵↵↵↵↵↵

0.81

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

0.79

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

0.79

POSITIVE LOGITS

 رغم

0.97

 oddly

0.96

 ведь

0.95

 Surprisingly

0.94

 Meski

0.92

 shockingly

0.88

 தவிர்க்க

0.85

 ciekaw

0.84

 Meanwhile

0.84

 strangely

0.83

Activations Density 0.142%