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

    Neuronpedia

    INDEX
    Explanations

    words related to attractiveness or desirability

    oai_token-act-pair · gpt-3.5-turbo

    references to attractiveness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    othe
    -0.78
    cedented
    -0.78
    bel
    -0.78
    ignt
    -0.72
    iche
    -0.71
    jer
    -0.71
    FIN
    -0.69
    cham
    -0.69
    REL
    -0.67
    rel
    -0.67
    POSITIVE LOGITS
     lure
    0.93
     attractive
    0.87
     proposition
    0.87
     Flavoring
    0.80
     targets
    0.79
     prospects
    0.74
     attractiveness
    0.73
    lihood
    0.73
     attract
    0.73
     enticing
    0.73
    Act Density 0.023%

    No Known Activations