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

    Neuronpedia

    INDEX
    Explanations

    graphs and data visualization in various contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    theless
    -0.70
    aneous
    -0.64
     Lomb
    -0.62
    Whe
    -0.62
    estinal
    -0.61
     granted
    -0.60
    ONT
    -0.60
     tradem
    -0.60
     charity
    -0.59
    ignt
    -0.59
    POSITIVE LOGITS
    ically
    1.17
    iq
    0.85
    graph
    0.83
    ical
    0.83
    ynt
    0.82
    osphere
    0.79
    alogy
    0.78
    ql
    0.77
    cape
    0.77
    ues
    0.77
    Act Density 7.301%

    No Known Activations