INDEX

Explanations

some thing or other

The neuron fires on interrogative words (e.g. “what,” “which,” “какой”) that introduce questions.

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

-1.52

-1.51

 готова

-1.49

 così

-1.48

-1.47

 from

-1.44

lho

-1.40

節約

-1.39

 политики

-1.38

 включая

-1.38

POSITIVE LOGITS

឵

1.86



1.71

ть

1.68

adell

1.64

汩

1.63

昻

1.61

傒

1.55

一篇

1.54

ﱠ

1.54

setPointSize

1.53

Activations Density 0.027%