INDEX

Explanations

in Africa

This neuron detects terms that appear as items in enumerated lists paired with numeric values.

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

ējās

-1.33

',

-1.30

 with

-1.27

vää

-1.22

ギリ

-1.22

'),

-1.20

get

-1.20

res

-1.19

:,

-1.19

you

-1.18

POSITIVE LOGITS

 which

1.32

くださった

1.25

нусы

1.24

 already

1.20

 podía

1.19

 betekent

1.19

Donde

1.18

 crece

1.18

チューム

1.16

はこの

1.15

Activations Density 0.155%