INDEX

Explanations

if any or if not

The neuron specifically detects occurrences of the conditional phrase “if any.”

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

you

-2.14

it

-2.13

他にも

-1.76

 there

-1.65

 tantôt

-1.59

 meisten

-1.59

ȼ

-1.57

どちらも

-1.54

گانه

-1.52

utilized

-1.52

POSITIVE LOGITS

她

1.70

就

1.64

russia

1.57

说

1.52

只是

1.51

 especiais

1.48

树

1.41

ные

1.41

не

1.41

ttar

1.40

Activations Density 0.025%