INDEX

Explanations

at the time

This neuron activates on the phrase “at the time” (and variants like “at the time of”), marking explicit temporal‐reference expressions.

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

to

-2.05

 from

-2.03

-1.95

two

-1.45

one

-1.45

 perhaps

-1.34

the

-1.33

})=

-1.27

 throughout

-1.27

 should

-1.26

POSITIVE LOGITS

 ceket

1.52

Sü

1.48

 autén

1.44

 grijs

1.44

حتی

1.42

 kalın

1.41

unków

1.41

it

1.40

 kumaş

1.39

目的是

1.39

Activations Density 0.036%