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

    Neuronpedia

    INDEX
    Explanations

    words related to a specific geographical location

    oai_token-act-pair · gpt-3.5-turbo

    references to the country New Zealand or its related aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    haps
    -0.76
    metic
    -0.74
    ramid
    -0.74
     deduct
    -0.72
    urations
    -0.68
     logical
    -0.67
     actu
    -0.66
    paying
    -0.65
    figured
    -0.64
    acity
    -0.64
    POSITIVE LOGITS
    eland
    1.10
     Islands
    0.76
    enegger
    0.74
    icz
    0.73
     Awakens
    0.73
    çIJ
    0.73
     Waters
    0.73
     AFB
    0.72
     Franch
    0.71
    ia
    0.70
    Act Density 0.003%

    No Known Activations