INDEX

Explanations

world war eras

The neuron flags occurrences of the word “War” (often together with its numeric or Roman‐numeral designation), i.e. explicit references to named wars or conflicts.

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

 durante

-1.16

 tijdens

-1.15

 during

-1.11

bezpiecz

-1.07

 během

-1.05

the

-1.02

 civilización

-1.00

 podczas

-0.99

 explotación

-0.95

 počas

-0.94

POSITIVE LOGITS

era

1.84

 period

1.35

Era

1.34

ERA

1.16

era

1.16

 timeframe

1.05

years

1.03

 years

1.03

yrs

0.89

II

0.88

Activations Density 0.033%