INDEX

Explanations

Dublin, Durbin, DbContext

The neuron strongly activates on occurrences of the place name “Dublin.”

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

</h3>

-2.72

</sub>

-2.64

nambuco

-2.45

蓠

-2.44

 consideran

-2.41

と思った

-2.39

The

-2.33

⏑

-2.31

 неизвест

-2.23

</strong>

-2.22

POSITIVE LOGITS

2.73

there

2.48

’

2.36

2.33

.''

2.19

鱟

2.17

on

2.09

what

2.08

 epitom

2.05

ၞ

2.05

Activations Density 0.001%