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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate decision-making and conditional scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucci
    -0.16
    iyat
    -0.16
    owie
    -0.15
    unik
    -0.15
     contin
    -0.14
    -deals
    -0.14
     Kız
    -0.14
    asurer
    -0.14
     rahat
    -0.14
    rego
    -0.14
    POSITIVE LOGITS
    åħĪ
    0.18
     process
    0.17
     åħĪ
    0.16
     steps
    0.16
    worthy
    0.15
     timeline
    0.15
    Delayed
    0.15
    process
    0.15
    illon
    0.14
    Steps
    0.14
    Act Density 0.013%

    No Known Activations