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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technology, innovation, and product descriptions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Based
    -0.69
    uid
    -0.65
    urden
    -0.65
    pa
    -0.65
    rio
    -0.64
    ãĥ¼ãĤ¯
    -0.63
    Exit
    -0.63
    hesis
    -0.62
    ensed
    -0.62
    obin
    -0.62
    POSITIVE LOGITS
     weddings
    1.04
     etc
    0.97
     hospitals
    0.86
     tennis
    0.83
     marriages
    0.83
    etc
    0.83
     automobiles
    0.83
     assorted
    0.82
     casinos
    0.81
     museums
    0.81
    Act Density 2.376%

    No Known Activations