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

    Neuronpedia

    INDEX
    Explanations

    people's names with double letters in them

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    cape
    -0.87
    natureconservancy
    -0.74
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.69
    20439
    -0.69
     bour
    -0.66
    ertodd
    -0.65
    cess
    -0.65
    ICT
    -0.64
     physic
    -0.64
    osterone
    -0.62
    POSITIVE LOGITS
    assian
    0.92
    ãģĨ
    0.91
    ians
    0.83
    aga
    0.81
    atory
    0.81
    ija
    0.80
    iak
    0.77
    essed
    0.75
    istically
    0.74
    isite
    0.74
    Act Density 0.095%

    No Known Activations