INDEX

Explanations

This file is part of

The neuron strongly fires on the first token of frequent multiword expressions (i.e. the lead word of common two‐word phrases).

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

</b>

-1.58

 vlož

-1.34

près

-1.34

🍡

-1.30

Already

-1.30

 svoju

-1.30

 variété

-1.27

 också

-1.24

 života

-1.23

cinq

-1.23

POSITIVE LOGITS

 there

2.36

 posibles

1.47

educt

1.44

there

1.40

 list

1.39

urnum

1.35

 competir

1.34

itées

1.31

();*/

1.30

 ello

1.30

Activations Density 0.105%