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

    Neuronpedia

    INDEX
    Explanations

    proper names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly Sharma and Gupta

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rique
    -0.84
    rants
    -0.80
    raltar
    -0.80
    enium
    -0.76
    icipated
    -0.74
    swick
    -0.73
    fig
    -0.72
    rified
    -0.72
    apego
    -0.72
    ª
    -0.72
    POSITIVE LOGITS
     Sharma
    1.23
     Rao
    0.91
     Gupta
    0.90
     Sunder
    0.84
     Kush
    0.77
     Ascend
    0.76
     Chou
    0.75
     Ng
    0.74
     HK
    0.74
     Singh
    0.73
    Act Density 0.025%

    No Known Activations