INDEX

Explanations

recognizable or identifiable

The neuron detects occurrences of the word “recognizable” (including its spelling variants and related morphological forms).

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

趼

-2.23

_{

-2.20

-2.19

rey

-2.09

oinette

-2.08

-2.05



-2.03

-2.02

鱚

-1.99

蹀

-1.98

POSITIVE LOGITS

其妙

2.31

 recognizable

2.09

in

2.05

聍

2.02

 recognisable

2.00

 dysfunctional

1.90

—

1.88

boots

1.85

绫

1.81

 così

1.80

Activations Density 0.005%