INDEX

Explanations

side-by-side and together

This neuron responds to phrases that describe two entities being placed, joined, or shared side by side or in parallel.

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

</h5>

-1.34

 know

-1.23

 have

-1.16

leftrightarrow

-1.15

 everyone

-1.14

ice

-1.13

 such

-1.10

 those

-1.09

</th>

-1.06

鼻

-1.04

POSITIVE LOGITS

Manfaat

1.52

Ꮀ

1.48

 cantora

1.25

 Perché

1.24

Vorte

1.24

dicionado

1.23

 الوزراء

1.23

 Dennoch

1.22

wenden

1.20

tividade

1.20

Activations Density 0.151%