INDEX

Explanations

it was who

This neuron activates on words that introduce or link clauses—especially relative pronouns (who, that, which) and copular forms (is, are, was, were).

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

of

-1.82

-1.62

any

-1.51

 anything

-1.44

𝖿

-1.43

two

-1.41

This

-1.40

-1.38

”？

-1.35

 anyone

-1.34

POSITIVE LOGITS

It

1.70

來

1.56

ும்

1.55

 однако

1.48

 ISNI

1.44

 numeral

1.44

力

1.40

saurus

1.37

が付

1.37

thérapie

1.34

Activations Density 0.012%