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

    Neuronpedia

    INDEX
    Explanations

    mentions of vacation resorts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of resorts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    older
    -0.75
    ector
    -0.74
    hemat
    -0.74
    APH
    -0.72
    rod
    -0.69
    ya
    -0.67
    RP
    -0.66
    corn
    -0.65
    aver
    -0.65
    yan
    -0.62
    POSITIVE LOGITS
     resort
    1.05
     resorts
    1.03
     Resort
    0.97
    ashtra
    0.79
     accommodation
    0.70
    reality
    0.67
     therap
    0.67
    igon
    0.67
     casinos
    0.66
     hotels
    0.66
    Act Density 0.004%

    No Known Activations