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

    Neuronpedia

    INDEX
    Explanations

    requests or invitations to take action

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating requests or offers to take actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ById
    -0.69
    soDeliveryDate
    -0.69
    hot
    -0.67
    DeliveryDate
    -0.66
     Moroc
    -0.65
    quickShipAvailable
    -0.65
    lies
    -0.65
    bars
    -0.65
     Said
    -0.65
    grounds
    -0.64
    POSITIVE LOGITS
     keep
    1.01
     partake
    1.00
     stay
    1.00
     participate
    0.98
     maximize
    0.98
     browse
    0.98
     broaden
    0.96
     give
    0.96
     submit
    0.96
     see
    0.95
    Act Density 0.073%

    No Known Activations