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

    Neuronpedia

    INDEX
    Explanations

    descriptive words that evoke strong emotions or imagery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    المكان
    -0.49
     Ordo
    -0.47
     الحره
    -0.47
     wireType
    -0.45
     [*]
    -0.44
    帖最后由
    -0.41
    <code>
    -0.40
    Condol
    -0.39
    Portály
    -0.39
     microfiber
    -0.39
    POSITIVE LOGITS
     attraction
    0.73
     enticing
    0.69
     alluring
    0.68
    attraction
    0.68
    attra
    0.68
     attracts
    0.68
     attractiveness
    0.66
     attractions
    0.66
     Attraction
    0.66
    Attra
    0.65
    Act Density 0.339%

    No Known Activations