INDEX

Explanations

investigations and probes

The neuron activates on terms and phrases that describe formal investigations or probes (e.g. investigated, under investigation, probe, investigating).

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

)}</

-1.34

)}$

-1.34

 dergleichen

-1.34

臯

-1.31

 AssemblyCompany

-1.27

regardless

-1.27

ón

-1.25

ཊ

-1.24

撸

-1.24

 gerçekten

-1.23

POSITIVE LOGITS

for

1.65

if

1.44

他

1.27

 focused

1.23

 znajdziesz

1.22

candidates

1.18

 focusing

1.16

詆

1.13

ajaan

1.12

 malah

1.12

Activations Density 0.057%