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

    Neuronpedia

    INDEX
    Explanations

    terms related to security systems and alarms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chat
    -0.16
    chat
    -0.16
     Chat
    -0.16
     Hurt
    -0.15
     Ban
    -0.14
    .Chat
    -0.14
     insert
    -0.14
     kê
    -0.14
    atha
    -0.13
     thrust
    -0.13
    POSITIVE LOGITS
     activation
    0.32
     triggered
    0.31
     activations
    0.30
    trigger
    0.29
    -trigger
    0.29
     trigger
    0.28
     Activation
    0.28
     activate
    0.28
    Activation
    0.28
     activated
    0.27
    Act Density 0.039%

    No Known Activations