INDEX

Explanations

i, i've

This neuron detects occurrences of the first‐person pronoun “I” (and forms like “I’m”).

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

of

-1.89

</td>

-1.83

 даже

-1.65

 would

-1.63

-1.59

-1.57

-1.52

-1.51

</h2>

-1.42

POSITIVE LOGITS

giy

1.56

 tekno

1.54

tiness

1.52



1.51

aimana

1.48

 personlig

1.47

 enlever

1.47

 撮り

1.45

wasn

1.45

partly

1.45

Activations Density 0.143%