INDEX

Explanations

qualifications or estimates

The main thing this neuron does is detect numeric values and quantitative specification language (e.g. figures, estimates, measurements, dates) 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

it

-1.15

jublj

-1.03

₃

-1.03

 dõi

-1.03

 الشرطة

-0.99

.*")]

-0.98

numsp

-0.97

స్త

-0.96

gilet

-0.96

บริการ

-0.96

POSITIVE LOGITS

 from

1.46

あくまで

1.45

 based

1.18

 которыми

1.17

 merely

1.17

for

1.10

are

1.05

そのため

1.01

あく

1.00

atillo

0.99

Activations Density 0.035%