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

    Neuronpedia

    INDEX
    Explanations

    dates and other information related to events or documents

    oai_token-act-pair · gpt-3.5-turbo

    metadata elements, particularly details about authors, dates, and descriptive tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     forgetting
    -0.70
    raq
    -0.66
     rede
    -0.65
     disg
    -0.64
     coughing
    -0.63
     Haram
    -0.63
     flee
    -0.62
    ysis
    -0.61
     shred
    -0.60
     forget
    -0.60
    POSITIVE LOGITS
    isine
    0.92
    escription
    0.90
    Status
    0.89
    Narr
    0.88
    ometown
    0.86
    Duration
    0.84
    podcast
    0.84
    price
    0.83
    Age
    0.82
    Date
    0.81
    Act Density 0.250%

    No Known Activations