INDEX

Explanations

specific syntactic and structural markers commonly used in formal mathematical notation and technical discourse

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

findpost

-0.82

<h5>

-0.73

 mín

-0.69

^{

-0.69

nbsp

-0.68

marvin

-0.67

 fact

-0.66

namic

-0.66

 Lilli

-0.66

 Gatt

-0.66

POSITIVE LOGITS

){\

1.09

{\

1.07

{\

0.97

_{{\

0.96

${\

0.96

}}}{\

0.96

{{\

0.94

}}_{\

0.93

${\

0.92

 useRef

0.91

Activations Density 15.690%