INDEX

Explanations

place names and locations

The neuron chiefly detects geographic place names (toponyms), i.e. names of towns, parks, counties, roads, preserves, etc.

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

 xícara

-1.43

ERICK

-1.39

 VEHICLE

-1.36

тивов

-1.30

cest

-1.30

misch

-1.29

yf

-1.29

ilya

-1.27

manteau

-1.23

 voltak

-1.23

POSITIVE LOGITS

new

1.43

of

1.40

1.38

 WITHOUT

1.31

ing

1.30

 AFTER

1.27

iencias

1.23

Ār

1.23

UnitTesting

1.22

 geboten

1.22

Activations Density 0.243%