INDEX

Explanations

one's singular self

The neuron activates on occurrences of the indefinite pronoun “one” (including “one’s”).

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

 каждого

-1.84

,'

-1.66

 each

-1.63

 других

-1.57

 všechny

-1.52

but

-1.49

 maksi

-1.48

是什么意思

-1.48

);

-1.46

 utilizzata

-1.46

POSITIVE LOGITS

to

1.96

℟

1.91

’

1.85

self

1.84

carnated

1.80

⎆

1.67

Ṛ

1.66

了一会儿

1.59

%;

1.59

entious

1.58

Activations Density 0.034%