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

    Neuronpedia

    INDEX
    Explanations

    references to luxury items or experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to luxury items or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    older
    -0.89
    unin
    -0.88
    nect
    -0.83
    ynthesis
    -0.79
    snap
    -0.77
    etts
    -0.77
    soType
    -0.75
    lis
    -0.75
    sis
    -0.74
    corn
    -0.72
    POSITIVE LOGITS
     suites
    0.92
     luxury
    0.92
     goods
    0.91
     boutique
    0.91
     sedan
    0.86
    itton
    0.86
     hotels
    0.85
     accommodations
    0.84
     apartments
    0.84
     condos
    0.81
    Act Density 0.036%

    No Known Activations