INDEX

Explanations

for you, myself, yourself

This neuron detects phrases expressing an emotion toward someone else, especially constructions like “[emotion] for [someone]” (e.g. “happy for you,” “excited for us,” “scared for yourself”).

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

 penyebab

-1.55

 contribute

-1.51

itato

-1.48

matian

-1.46

apatan

-1.45

༐

-1.43

laje

-1.41

 он

-1.41



-1.40

So

-1.38

POSITIVE LOGITS

2.23

will

1.69

():

1.65

1.64

(!)

1.60

 tanken

1.59

 kapas

1.58

 namun

1.55

 dekoratif

1.54

 見る

1.53

Activations Density 0.006%