INDEX

Explanations

. marks end of statement

This neuron activates on numeric tokens (digits and numbers) in the text.

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

 this

-1.13

 with

-1.05

 also

-1.00

-0.98

for

-0.98

 such

-0.95

🤌

-0.92

-0.90

 from

-0.89

POSITIVE LOGITS

 después

1.52

雖然

1.51

 PEOPLE

1.44

虽然

1.41

 после

1.41

 fans

1.30

according

1.27

期间

1.27

during

1.24

 بعد

1.23

Activations Density 0.019%