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

    Neuronpedia

    INDEX
    Explanations

    names of countries and actions related to politics and decisions made by government bodies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONSORED
    -0.90
    uca
    -0.77
    pless
    -0.73
    abal
    -0.71
    xual
    -0.69
    icent
    -0.69
    misc
    -0.68
    acebook
    -0.68
    OPA
    -0.67
    APE
    -0.66
    POSITIVE LOGITS
     York
    1.27
     Zealand
    1.27
    foundland
    1.22
     Orleans
    1.19
    bie
    1.18
    bies
    1.16
     arrivals
    1.06
     Hampshire
    1.05
    castle
    0.98
     YORK
    0.98
    Act Density 0.060%

    No Known Activations