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

    Neuronpedia

    INDEX
    Explanations

    organization or institution names

    oai_token-act-pair · gpt-3.5-turbo

    prominent names and entities in academia, business, and research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aepernick
    -0.74
    pez
    -0.69
    orius
    -0.69
    jriwal
    -0.68
    liest
    -0.68
    afia
    -0.68
    avez
    -0.68
    yip
    -0.67
    glers
    -0.66
    venge
    -0.65
    POSITIVE LOGITS
     Brothers
    1.04
     Institution
    0.96
     Institute
    0.96
     Companies
    0.92
     Prize
    0.91
     Journalism
    0.86
     Bros
    0.86
     Associates
    0.86
     Laboratories
    0.85
     Fellow
    0.84
    Act Density 0.245%

    No Known Activations