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

    Neuronpedia

    INDEX
    Explanations

    information related to statistics, measurements, and data

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and their context, particularly related to measurements and statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     parad
    -0.77
     behav
    -0.75
    ²¾
    -0.74
     sugg
    -0.73
     behavi
    -0.69
     headlights
    -0.68
     lia
    -0.67
     inform
    -0.67
     interchange
    -0.67
     obser
    -0.67
    POSITIVE LOGITS
    Ranked
    0.94
     Including
    0.94
    total
    0.94
     Avg
    0.88
    Total
    0.88
     avg
    0.86
    average
    0.86
     Rated
    0.81
     Average
    0.80
     Total
    0.80
    Act Density 0.273%

    No Known Activations