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

    Neuronpedia

    INDEX
    Explanations

    references to geographical locations, specifically cities and universities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific geographic locations and institutions, particularly Syracuse and Albany

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    teen
    -1.01
    wagen
    -0.87
    oos
    -0.86
    maker
    -0.81
    quet
    -0.81
    rior
    -0.79
    away
    -0.78
    croft
    -0.75
    roxy
    -0.74
    making
    -0.73
    POSITIVE LOGITS
    ymes
    0.92
     Schumer
    0.78
     sqor
    0.73
     Parish
    0.73
    é¾įå¥ij士
    0.72
    à¼
    0.71
     UNIVERS
    0.67
     Mn
    0.66
     TAMADRA
    0.66
    ideon
    0.66
    Act Density 0.099%

    No Known Activations