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

    Neuronpedia

    INDEX
    Explanations

    pairs of names of famous individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to influential public figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.72
    fw
    -0.71
     compound
    -0.70
    tera
    -0.69
     SERVICES
    -0.68
    abus
    -0.68
    FIX
    -0.67
     redes
    -0.66
    isks
    -0.65
     inland
    -0.65
    POSITIVE LOGITS
     Oprah
    1.28
     Ronald
    1.27
     Barack
    1.26
     Tony
    1.26
     George
    1.25
     Adolf
    1.25
     Jimmy
    1.25
     John
    1.22
     Vladimir
    1.22
     Winston
    1.21
    Act Density 0.225%

    No Known Activations