INDEX

Explanations

numbers and conjunctions

This neuron does not activate on any of the shown tokens and appears to be effectively inactive (i.e. it finds nothing).

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

is

-1.49

 geprü

-1.45

 sentimiento

-1.45

 vielfach

-1.44

 prevé

-1.41

 muitas

-1.39

 molte

-1.35

 contribuye

-1.35

 creó

-1.35

㈱

-1.33

POSITIVE LOGITS

or

2.27

but

1.65

and

1.47

مپ

1.45

 piernas

1.34

nables

1.31

igens

1.30

bungen

1.29

}^{+}

1.28

}^{+}$

1.28

Activations Density 0.059%