INDEX

Explanations

The neuron fires specifically on JavaScript/TypeScript “let” variable‐declaration keywords.

variable declarations using let

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

觏

-2.34

Ꮞ

-2.28

葙

-2.13

hombres

-2.11

März

-2.05

不可思议

-2.02

Ꮸ

-1.99

 allerlei

-1.98

Nguy

-1.93

 sudadera

-1.93

POSITIVE LOGITS

2.61

2.58

];

1.91

шего

1.89

);

1.77

1.76

]},

1.66

 апреля

1.64

 либо

1.64

 где

1.63

Activations Density 0.003%