Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions of love and emotional connections between individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    出版年
    -0.77
     مرئيه
    -0.75
    ंदीखरीदारी
    -0.69
    webElement
    -0.67
     Roskov
    -0.66
     estekak
    -0.65
     تضيفلها
    -0.64
     nakalista
    -0.63
     ſtre
    -0.62
    }`).
    -0.62
    POSITIVE LOGITS
     loved
    1.04
     affection
    0.96
     love
    0.88
    loved
    0.84
     loves
    0.80
     beloved
    0.80
     cariño
    0.78
     Affection
    0.73
     affections
    0.73
     LOVED
    0.72
    Act Density 0.214%

    No Known Activations