INDEX

Explanations

found himself, herself, themselves

The neuron predominantly activates on occurrences of the verb “find” (in forms like find, finds, found).

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

냑

-1.64

-1.55

-1.53

on

-1.47

 dotyczą

-1.38

步

-1.35

喁

-1.34

setcounter

-1.34

 новое

-1.32

POSITIVE LOGITS

 with

1.56

我们就

1.52

 their

1.51

 mereka

1.45

 ставить

1.41

 pengertian

1.40

 خواهد

1.37

may

1.34

reiben

1.32

 will

1.31

Activations Density 0.009%