INDEX

Explanations

capture or catch

The main thing this neuron does is identify occurrences of the verb “catch” (and its past-tense and related forms like “captured”).

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

 داخ

-1.40

!（

-1.37

绚

-1.36

🤘

-1.34

骤

-1.33

 that

-1.30

釓

-1.30

 dolce

-1.29

峮

-1.29

ки

-1.27

POSITIVE LOGITS

мія

1.60

 Then

1.58

 Only

1.56

 Füßen

1.56

 satisfy

1.54

 That

1.52

꜆

1.52

 необхідно

1.51

 capture

1.49

 glimpse

1.49

Activations Density 0.017%