INDEX

Explanations

members of the

The neuron fires on numeric tokens (e.g. standalone digits or numbers).

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

);

-2.13

 periódicos

-1.97

,"

-1.94

个

-1.93

,'

-1.92

𝔨

-1.90

 críticos

-1.89

 estadounidenses

-1.89

).

-1.86

both

-1.84

POSITIVE LOGITS

For

2.19

you

2.06

 Некоторые

2.00

鵟

1.87

quelize

1.86

𖥧

1.86

the

1.84

謌

1.76

ar

1.74

då

1.66

Activations Density 0.019%