INDEX

Explanations

be followed by adjective or past participle

The neuron strongly activates on occurrences of the verb “be” (all its forms).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 allerlei

-1.89

攫

-1.74

&#

-1.67

 boîtier

-1.63

 helicóptero

-1.61

 farol

-1.59

坼

-1.57

 OGSÅ

-1.55

zyw

-1.54

</th>

-1.52

POSITIVE LOGITS

↵

2.03

be

1.95

私に

1.84

 furent

1.82

一応

1.80

to

1.74

焌

1.70

一緒に

1.69

私には

1.63

를

1.63

Activations Density 0.010%