INDEX

Explanations

принимает

This neuron fires on the literal LaTeX token “text” (as in \text{…}) within math‐mode markup.

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

These

-2.50

Their

-2.27

 thier

-1.93

They

-1.93

Those

-1.82

趼

-1.80

 Honestly

-1.77

 Bringing

-1.76

There

-1.75

 Their

-1.75

POSITIVE LOGITS

⢌

2.45

囁

2.02

-:

1.98

 tył

1.97

 segredo

1.93

gemeester

1.89

椙

1.88

᠂

1.87

Activations Density 0.001%