INDEX

Explanations

finding solutions or describing function

This neuron detects (primarily content) verbs in various tenses.

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

 there

-1.36

Akhir

-1.20

 тут

-1.17

也有

-1.14

鍬

-1.10

ंट

-1.09

المصدر

-1.08

 Bedingungen

-1.07

こちらも

-1.07

itées

-1.06

POSITIVE LOGITS

 like

1.92

 such

1.50

),

1.40

who

1.30

 with

1.27

and

1.26

 that

1.21

 whose

1.20

 this

1.20

ность

1.19

Activations Density 0.106%