INDEX

Explanations

components and parts

This neuron fires most strongly on technical product or part names and their specification codes (e.g. fasteners, bolts, nuts, bearing types, ASTM numbers).

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

-1.28

sklä

-1.20

 Verbrechen

-1.17

 ciudadana

-1.15

inine

-1.13

んだよね

-1.11

ämie

-1.10

 cadeia

-1.10

 ativar

-1.10

-1.09

POSITIVE LOGITS

for

1.41

 séries

1.38

bentuk

1.34

 arvo

1.34

 with

1.30

 sizes

1.30

 también

1.27

 сериал

1.26

 zapato

1.23

 olvidado

1.23

Activations Density 0.070%