INDEX

Explanations

words starting with T

The neuron detects capitalized personal names and initials (e.g. author surnames and name initials).

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

 помню

-1.64

 dieser

-1.56

胧

-1.55

⿷

-1.54

 bears

-1.53



-1.50

ॲ

-1.48

-1.45

 espírito

-1.42

avras

-1.42

POSITIVE LOGITS

</h5>

1.91

ate

1.83

1.66

</td>

1.56

</i>

1.47

л

1.46

1.41

人们

1.40

телем

1.39

old

1.37

Activations Density 0.061%