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

    Neuronpedia

    INDEX
    Explanations

    numerical values and units of measure

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with time periods or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CLS
    -0.61
     Barrett
    -0.57
    imb
    -0.56
    ****************
    -0.56
    press
    -0.56
     BG
    -0.55
    ARA
    -0.55
    Scene
    -0.55
     »
    -0.54
    payers
    -0.54
    POSITIVE LOGITS
     respectively
    0.93
    soDeliveryDate
    0.75
     hers
    0.72
    ).[
    0.71
     thereof
    0.71
    )).
    0.70
    aeus
    0.70
     theirs
    0.70
    arettes
    0.69
     thereafter
    0.67
    Act Density 1.210%

    No Known Activations