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

    Neuronpedia

    INDEX
    Explanations

    place names or possibly locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ģ«
    -0.79
    PDATE
    -0.77
    ï¸
    -0.71
    drm
    -0.71
    SOURCE
    -0.71
    Termin
    -0.70
    ¯
    -0.70
     Archdemon
    -0.68
     Featured
    -0.67
     referen
    -0.66
    POSITIVE LOGITS
    puff
    0.92
    jee
    0.74
    erella
    0.74
    ippi
    0.73
    uppet
    0.72
     AFB
    0.72
    itiveness
    0.71
    igans
    0.71
    ridge
    0.69
    auga
    0.69
    Act Density 0.234%

    No Known Activations