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

    Neuronpedia

    INDEX
    Explanations

    names of universities or educational institutions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    WARD
    -0.81
    itives
    -0.79
    ences
    -0.78
    ports
    -0.77
    rahim
    -0.73
    ged
    -0.69
     Gors
    -0.69
    enced
    -0.68
    ded
    -0.68
    nings
    -0.68
    POSITIVE LOGITS
    bones
    0.93
    agne
    0.85
    anooga
    0.82
    ron
    0.79
    avez
    0.77
    osen
    0.75
    bara
    0.74
    aign
    0.72
    unin
    0.71
    icago
    0.70
    Act Density 0.059%

    No Known Activations