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

    Neuronpedia

    INDEX
    Explanations

    names of countries

    oai_token-act-pair · gpt-3.5-turbo

    references to the country Cameroon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ters
    -0.77
    strous
    -0.74
    rix
    -0.73
    nings
    -0.71
    ially
    -0.70
    thritis
    -0.68
    haust
    -0.68
    thin
    -0.66
    ptive
    -0.66
    Beer
    -0.66
    POSITIVE LOGITS
    wana
    0.82
     sarc
    0.80
    arov
    0.77
     Ou
    0.76
    addafi
    0.75
     chimpanzees
    0.75
     autom
    0.74
    ofi
    0.72
     chimpan
    0.71
    atory
    0.71
    Act Density 0.035%

    No Known Activations