INDEX

Explanations

quotes and punctuation

The neuron is triggered by quotation‐mark characters (i.e. text opening or closing quotes).

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

ﮕ

-2.53

Elaboración

-2.06

っす

-2.05

 同人

-1.99

 CAMPAIGN

-1.93

)」

-1.92

 BRAZIL

-1.91

 ولكن

-1.91

 BIRDS

-1.91

 PUBL

-1.89

POSITIVE LOGITS

2.80

actéristi

2.72

2.56

 they

2.55

荭

2.33

2.23

2.06

1.98

1.96

1.94

Activations Density 0.008%