INDEX

Explanations

equality comparison operators

The neuron fires on tokens related to equality checks—i.e. occurrences of “equal,” “equals,” or equality operators (==, ===).

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

èbres

-1.03

setAdapter

-0.95

MLLoader

-0.92

is

-0.91

LEncoder

-0.90

PCell

-0.88

ᚾ

-0.88

}}_{

-0.88

 απε

-0.86

🕗

-0.86

POSITIVE LOGITS

to

1.73

IgnoreCase

1.22

(=)

1.06

ignore

0.96

 gaji

0.92

 изобре

0.88

りする

0.84

 popolari

0.84

ignor

0.84

 anbef

0.84

Activations Density 0.009%