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

    Neuronpedia

    INDEX
    Explanations

    names of political figures or organizations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ùĩ
    -0.68
     caution
    -0.67
    MORE
    -0.62
    oise
    -0.62
     Rica
    -0.59
     Hels
    -0.59
    hold
    -0.59
     Haz
    -0.59
     Albion
    -0.58
     Saud
    -0.57
    POSITIVE LOGITS
    ptoms
    1.31
    pson
    1.30
    posium
    1.16
    otor
    1.03
    aceutical
    0.96
    otion
    0.93
    ichael
    0.91
    otos
    0.90
    achine
    0.90
    iasm
    0.89
    Act Density 0.017%

    No Known Activations