INDEX

Explanations

mid-

The neuron fires on occurrences of the word “mid” (as in “mid-1960s,” “mid-Christchurch,” “mid-latitude,” etc.), i.e. the “mid-” prefix marking the middle of a time or spatial range.

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

-3.22

of

-3.02

to

-2.81

 zwölf

-2.70

↵

-2.69

 särskilt

-2.58

.’

-2.56

-“

-2.56

 ‘‘

-2.52

 zwanzig

-2.52

POSITIVE LOGITS

鄚

3.27

 fédé

2.98

Setelah

2.75

 espr

2.66

Sebelum

2.64

 решила

2.64

Kondisi

2.59

Spesifikasi

2.59

ቼ

2.56

Sekarang

2.55

Activations Density 0.024%