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

    Neuronpedia

    INDEX
    Explanations

    phrases related to refusal or non-compliance with a request or action

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating refusal or resistance to performing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.99
     Compass
    -0.78
    lined
    -0.76
    oen
    -0.72
    quickShipAvailable
    -0.69
     Header
    -0.69
    Line
    -0.68
    ////////////////////////////////
    -0.68
    retty
    -0.67
    GW
    -0.67
    POSITIVE LOGITS
     accept
    1.18
     endorse
    1.12
     participate
    1.08
     cooperate
    1.08
     reproduce
    1.07
     comply
    1.05
     obey
    1.04
     recognize
    1.04
     settle
    1.04
     acknowledge
    1.03
    Act Density 0.061%

    No Known Activations