INDEX

Explanations

do/did/does followed by under or not

The neuron activates on occurrences of the auxiliary/main verb “do” (including its forms “does” and “doesn’t”).

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

臜

-1.48

 таких

-1.48

 cordones

-1.47

哙

-1.45

 exé

-1.41

ザイン

-1.39

茈

-1.38

튿

-1.38

鴕

-1.38

 appeler

-1.38

POSITIVE LOGITS

if

1.72

 people

1.66

 their

1.64

1.62

 various

1.61

so

1.61

1.60

 different

1.58

 some

1.57

 this

1.52

Activations Density 0.038%