INDEX

Explanations

converting or changing form

This neuron detects words and phrases that describe transforming or converting one thing into another (e.g. “turn…into,” “replace…as,” “put…into,” “make”).

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

and

-2.25

to

-1.64

)},

-1.30

्रेस

-1.13

)$,

-1.10

 normais

-1.09

)),

-1.09

 preferido

-1.09

autoreleasepool

-1.09

]';

-1.08

POSITIVE LOGITS

 wydaje

1.34

想了想

1.27

 légèrement

1.21

 barbati

1.20

 weirdly

1.20

 naprawdę

1.17

 Pires

1.17

 никто

1.17

niejs

1.16

 inherently

1.16

Activations Density 0.079%