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

    Neuronpedia

    INDEX
    Explanations

    instances of people talking or discussing

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    iru
    -0.72
    MJ
    -0.69
    rish
    -0.63
    Present
    -0.62
    MI
    -0.62
    apo
    -0.61
    next
    -0.59
    ))))
    -0.58
     remembers
    -0.57
    States
    -0.56
    POSITIVE LOGITS
     lately
    1.25
     since
    1.15
     countless
    1.04
     numerous
    0.97
     recently
    0.90
     extensively
    0.90
    since
    0.88
     innumerable
    0.88
     hitherto
    0.86
     steadily
    0.79
    Act Density 2.899%

    No Known Activations